1
|
Metcalf O, Lamb KE, Forbes D, O’Donnell ML, Qian T, Varker T, Cowlishaw S, Zaloumis S. Predicting high anger intensity using ecological momentary assessment and wearable-derived physiological data in a trauma-affected sample. Eur J Psychotraumatol 2025; 16:2472485. [PMID: 40135377 PMCID: PMC11948352 DOI: 10.1080/20008066.2025.2472485] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/18/2024] [Revised: 01/31/2025] [Accepted: 02/18/2025] [Indexed: 03/27/2025] Open
Abstract
Background: Digital technologies offer tremendous potential to predict dysregulated mood and behavior within an individual's environment, and in doing so can support the development of new digital health interventions. However, no prediction models have been built in trauma-exposed populations that leverage real-world data.Objective: This project aimed to determine if wearable-derived physiological data can predict anger intensity in trauma-exposed adults.Method: Heart rate variability (i.e. a commercial wearable stress score) was combined with ecological momentary assessment (EMA) data collected over 10 days (n = 84). Five summary measures from stress scores collected 10 min prior to each EMA were selected using factor analysis of 24 candidates.Results: A high area under the receiver operating curve (AUC) was found for a logistic mixed effects model including these measures as predictors, ranging 0.761 (95% CI:0.569-0.921) to 0.899 (95% CI:0.784-0.980) across cross-validation methods.Conclusions: While the predictive performance may be overly optimistic due to the outcome prevalence (13.8%) and requires replication with larger datasets, our promising findings have significant methodological and clinical implications for researchers looking to build novel prediction and treatment approaches to respond to posttraumatic mental health.
Collapse
Affiliation(s)
- Olivia Metcalf
- Phoenix Australia – Centre for Posttraumatic Mental Health, Department of Psychiatry, University of Melbourne, Carlton, Australia
- Centre for Digital Transformation of Health, University of Melbourne, Carlton, Australia
| | - Karen E. Lamb
- Centre for Epidemiology and Biostatistics, Melbourne School of Population and Global Health, University of Melbourne, Carlton, Australia
- MISCH (Methods and Implementation Support for Clinical Health) Research Hub, Faculty of Medicine, Dentistry, and Health Sciences, University of Melbourne, Carlton, Australia
| | - David Forbes
- Phoenix Australia – Centre for Posttraumatic Mental Health, Department of Psychiatry, University of Melbourne, Carlton, Australia
| | - Meaghan L. O’Donnell
- Phoenix Australia – Centre for Posttraumatic Mental Health, Department of Psychiatry, University of Melbourne, Carlton, Australia
| | - Tianchen Qian
- Department of Statistics, University of California, Irvine, Irvine, CA, USA
| | - Tracey Varker
- Phoenix Australia – Centre for Posttraumatic Mental Health, Department of Psychiatry, University of Melbourne, Carlton, Australia
| | - Sean Cowlishaw
- Turner Institute for Brain and Mental Health, Monash School of Psychological Sciences, Monash University, Clayton, Australia
| | - Sophie Zaloumis
- Centre for Epidemiology and Biostatistics, Melbourne School of Population and Global Health, University of Melbourne, Carlton, Australia
- MISCH (Methods and Implementation Support for Clinical Health) Research Hub, Faculty of Medicine, Dentistry, and Health Sciences, University of Melbourne, Carlton, Australia
| |
Collapse
|
2
|
Vos G, Ebrahimpour M, van Eijk L, Sarnyai Z, Rahimi Azghadi M. Stress monitoring using low-cost electroencephalogram devices: A systematic literature review. Int J Med Inform 2025; 198:105859. [PMID: 40056845 DOI: 10.1016/j.ijmedinf.2025.105859] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2024] [Revised: 02/27/2025] [Accepted: 03/01/2025] [Indexed: 03/10/2025]
Abstract
INTRODUCTION The use of low-cost, consumer-grade wearable health monitoring devices has become increasingly prevalent in mental health research, including stress studies. While cortisol response magnitude remains the gold standard for stress assessment, an expanding body of research employs low-cost EEG devices as primary tools for recording biomarker data, often combined with wrist and ring-based wearables. However, the technical variability among low-cost EEG devices, particularly in sensor count and placement according to the 10-20 Electrode Placement System, poses challenges for reproducibility in study outcomes. OBJECTIVE This review aims to provide an overview of the growing application of low-cost EEG devices and machine learning techniques for assessing brain function, with a focus on stress detection. It also highlights the strengths and weaknesses of various machine learning methods commonly used in stress research, and evaluates the reproducibility of reported findings along with sensor count and placement importance. METHODS A comprehensive review was conducted of published studies utilizing EEG devices for stress detection and their associated machine learning approaches. Searches were performed across databases including Scopus, Google Scholar, ScienceDirect, Nature, and PubMed, yielding 69 relevant articles for analysis. The selected studies were synthesized into four thematic categories: stress assessment using EEG, low-cost EEG devices, datasets for EEG-based stress measurement, and machine learning techniques for EEG-based stress analysis. For machine learning-focused studies, validation and reproducibility methods were critically assessed. Study quality was evaluated and scored using the IJMEDI checklist. RESULTS The review identified several studies employing low-cost EEG devices to monitor brain activity during stress and relaxation phases, with many reporting high predictive accuracy using various machine learning validation techniques. However, only 54% of the studies included health screening prior to experimentation, and 58% were categorized as low-powered due to limited sample sizes. Additionally, few studies validated their results using an independent validation set or cortisol response as a correlating biomarker and there was a lack of consensus on data pre-processing and sensor placement as a key contributor to improving model generalization and accuracy. CONCLUSION Low-cost consumer-grade wearable devices, including EEG and wrist-based monitors, are increasingly utilized in stress-related research, offering promising avenues for non-invasive biomarker monitoring. However, significant gaps remain in standardizing EEG signal processing and sensor placement, both of which are critical for enhancing model generalization and accuracy. Furthermore, the limited use of independent validation sets and cortisol response as correlating biomarkers highlights the need for more robust validation methodologies. Future research should focus on addressing these limitations and establishing consensus on data pre-processing techniques and sensor configurations to improve the reliability and reproducibility of findings in this growing field.
Collapse
Affiliation(s)
- Gideon Vos
- College of Science and Engineering, James Cook University, James Cook Dr, Townsville, 4811, QLD, Australia
| | - Maryam Ebrahimpour
- College of Science and Engineering, James Cook University, James Cook Dr, Townsville, 4811, QLD, Australia
| | - Liza van Eijk
- College of Health Care Sciences, James Cook University, James Cook Dr, Townsville, 4811, QLD, Australia
| | - Zoltan Sarnyai
- College of Public Health, Medical, and Vet Sciences, James Cook University, James Cook Dr, Townsville, 4811, QLD, Australia
| | - Mostafa Rahimi Azghadi
- College of Science and Engineering, James Cook University, James Cook Dr, Townsville, 4811, QLD, Australia.
| |
Collapse
|
3
|
Menassa M, Wilmont I, Beigrezaei S, Knobbe A, Arita VA, Valderrama JF, Bridge L, Verschuren WMM, Rennie KL, Franco OH, van der Ouderaa F. The future of healthy ageing: Wearables in public health, disease prevention and healthcare. Maturitas 2025; 196:108254. [PMID: 40157094 DOI: 10.1016/j.maturitas.2025.108254] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2024] [Revised: 03/10/2025] [Accepted: 03/21/2025] [Indexed: 04/01/2025]
Abstract
Wearables have evolved into accessible tools for sports, research, and interventions. Their use has expanded to real-time monitoring of behavioural parameters related to ageing and health. This paper provides an overview of the literature on wearables in disease prevention and healthcare over the life course (not only in the older population), based on insights from the Future of Diagnostics Workshop (Leiden, January 2024). Wearable-generated parameters include blood glucose, heart rate, step count, energy expenditure, and oxygen saturation. Integrating wearables in healthcare is protracted and far from mainstream implementation, but promises better diagnosis, biomonitoring, and assessment of medical interventions. The main lifestyle factors monitored directly with wearables or through smartphone applications for disease prevention include physical activity, energy expenditure, gait, sleep, and sedentary behaviour. Insights on dietary consumption and nutrition have resulted from continuous glucose monitors. These factors are important for healthy ageing due to their effect on underlying disease pathways. Inclusivity and engagement, data quality and ease of interpretation, privacy and ethics, user autonomy in decision making, and efficacy present challenges to but also opportunities for their use, especially by older people. These need to be addressed before wearables can be integrated into mainstream medical and public health strategies. Furthermore, six key considerations need to be tackled: 1) engagement, health literacy, and compliance with personalised feedback, 2) technical and standardisation requirements for scalability, 3) accountability, data safety/security, and ethical concerns, 4) technological considerations, access, and capacity building, 5) clinical relevance and risk of overdiagnosis/overmedicalisation, and 6) the clinician's perspective in implementation.
Collapse
Affiliation(s)
- Marilyne Menassa
- Department of Global Public Health & Bioethics, Julius Center for Health Science and Primary Care, UMC Utrecht, Utrecht University, the Netherlands.
| | - Ilona Wilmont
- Institute for Computing and Information Sciences, Data Science, Radboud University Nijmegen, Nijmegen, the Netherlands; Stichting Je Leefstijl Als Medicijn, the Netherlands
| | - Sara Beigrezaei
- Department of Global Public Health & Bioethics, Julius Center for Health Science and Primary Care, UMC Utrecht, Utrecht University, the Netherlands
| | - Arno Knobbe
- Leiden Institute of Advanced Computer Science, Universiteit Leiden, Leiden, the Netherlands
| | - Vicente Artola Arita
- Department of Global Public Health & Bioethics, Julius Center for Health Science and Primary Care, UMC Utrecht, Utrecht University, the Netherlands
| | - Jose F Valderrama
- Department of Global Public Health & Bioethics, Julius Center for Health Science and Primary Care, UMC Utrecht, Utrecht University, the Netherlands
| | - Lara Bridge
- Department of Global Public Health & Bioethics, Julius Center for Health Science and Primary Care, UMC Utrecht, Utrecht University, the Netherlands
| | - W M Monique Verschuren
- Department of Global Public Health & Bioethics, Julius Center for Health Science and Primary Care, UMC Utrecht, Utrecht University, the Netherlands; National Institute for Public Health and the Environment, Bilthoven, the Netherlands
| | - Kirsten L Rennie
- MRC Epidemiology Unit, University of Cambridge, Cambridge, United Kingdom
| | - Oscar H Franco
- Department of Global Public Health & Bioethics, Julius Center for Health Science and Primary Care, UMC Utrecht, Utrecht University, the Netherlands
| | | |
Collapse
|
4
|
Byfield R, Yang I, Higgins M, Carlson N. A Scoping Review of Studies Reporting Heart Rate Variability Measurement Among Pregnant and Postpartum People Using Wearable Technology. Biol Res Nurs 2025:10998004251325212. [PMID: 40126360 DOI: 10.1177/10998004251325212] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/25/2025]
Abstract
Maternal mental health conditions significantly contribute to pregnancy-related mortality in the United States. Approximately 20-25% of postnatal women exhibit symptoms of depressive and anxiety disorders. Mental health is influenced by stress, which affects mood, cognition, and behavior. Heart rate variability (HRV), the time interval between consecutive heartbeats, is a physiological marker for assessing stress levels, providing critical insights into the body's autonomic responses. Wearable devices measuring HRV offer a non-invasive method to monitor stress and mental health, enabling early detection of maternal stress dynamics to facilitate timely interventions. In this scoping review, we aimed to capture the current state of science on two areas of focus: (1) utilization of wearable technology for HRV monitoring in pregnant and postpartum women, (2) findings from these perinatal HRV studies, including observed HRV trends throughout pregnancy and postpartum, as well as the association between HRV, perinatal stress, and mental health. The six included perinatal HRV studies employed five fitness tracking wearables, utilizing either periodic or continuous 24-h monitoring. Findings include evidence that HRV declines during pregnancy, with a return to normal levels postpartum. Associations between HRV and stress were inconsistent across studies, with some demonstrating correlations and others reporting no relationship. Postpartum HRV measurements effectively differentiated between women with postpartum depression (PPD) versus those with adjustment disorder (AJD), demonstrating high diagnostic accuracy. In this scoping review, HRV shows promise as a stress biomarker among pregnant/postpartum people, although more work is needed to standardize optimal methods of wearable HRV measurement in this population.
Collapse
|
5
|
Gu X, Hu X. Research on mood monitoring and intervention for anxiety disorder patients based on deep learning wearable devices. Technol Health Care 2025; 33:1128-1139. [PMID: 40105160 DOI: 10.1177/09287329241291376] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/20/2025]
Abstract
BackgroundAnxiety disorders are common mental health issues that have a significant effect on people's quality of life. Conventional techniques for tracking emotional states frequently lack the accuracy and sensitivity needed for successful intervention.ObjectivesThis project aims to create a sophisticated monitoring system that uses deep learning methods to evaluate physiological data from wearables, emphasizing heart rate variability (HRV), to forecast patients' emotional states who suffer from anxiety disorders.MethodsWearable equipment monitors physiological characteristics, which we used to obtain patient HRV data. We processed the data using a Bidirectional Long-Short-Term Memory (Bi-LSTM) network to evaluate time-dependent variables and enhance the precision of emotional state predictions. The physiological signals were used to teach the model to recognize different emotional states, such as neutral, happy, and sad.ResultsOutperforming conventional machine learning models, the Bi-LSTM model showed a high accuracy rate of up to 97% in predicting emotional states. The findings suggest that ongoing HRV monitoring can accurately track shifts in emotional states and enable prompt responses.ConclusionThis work emphasizes the possibility of real-time emotional state monitoring in patients with anxiety disorders with wearable technology and deep learning. The results point to the potential benefits of this strategy for improving emotional regulation and improving anxiety sufferers' quality of life, opening new avenues for investigation and advancement in the field of mental health therapies.
Collapse
Affiliation(s)
- Xiao Gu
- College of Teachers, Chengdu University, Chengdu, Sichuan, China
| | - Xuedan Hu
- School of Education, City University of Macau, Macau, China
| |
Collapse
|
6
|
Clemente-Suárez VJ, Martín-Rodríguez A, Curiel-Regueros A, Rubio-Zarapuz A, Tornero-Aguilera JF. Neuro-Nutrition and Exercise Synergy: Exploring the Bioengineering of Cognitive Enhancement and Mental Health Optimization. Bioengineering (Basel) 2025; 12:208. [PMID: 40001727 PMCID: PMC11851474 DOI: 10.3390/bioengineering12020208] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2024] [Revised: 02/14/2025] [Accepted: 02/17/2025] [Indexed: 02/27/2025] Open
Abstract
The interplay between nutrition, physical activity, and mental health has emerged as a frontier in bioengineering research, offering innovative pathways for enhancing cognitive function and psychological resilience. This review explores the neurobiological mechanisms underlying the synergistic effects of tailored nutritional strategies and exercise interventions on brain health and mental well-being. Key topics include the role of micronutrients and macronutrients in modulating neurogenesis and synaptic plasticity, the impact of exercise-induced myokines and neurotrophins on cognitive enhancement, and the integration of wearable bioelectronics for personalized monitoring and optimization. By bridging the disciplines of nutrition, psychology, and sports science with cutting-edge bioengineering, this review highlights translational opportunities for developing targeted interventions that advance mental health outcomes. These insights are particularly relevant for addressing global challenges such as stress, anxiety, and neurodegenerative diseases. The article concludes with a roadmap for future research, emphasizing the potential of bioengineered solutions to revolutionize preventive and therapeutic strategies in mental health care.
Collapse
Affiliation(s)
- Vicente Javier Clemente-Suárez
- Faculty of Sport Sciences, Universidad Europea de Madrid, Villaviciosa de Odón, 28670 Madrid, Spain; (V.J.C.-S.); (A.M.-R.); (A.C.-R.)
- Grupo de Investigación en Cultura, Educación y Sociedad, Universidad de la Costa, Barranquilla 080002, Colombia
| | - Alexandra Martín-Rodríguez
- Faculty of Sport Sciences, Universidad Europea de Madrid, Villaviciosa de Odón, 28670 Madrid, Spain; (V.J.C.-S.); (A.M.-R.); (A.C.-R.)
- Faculty of Applied Social Sciences and Communications, UNIE, 28015 Madrid, Spain
| | - Agustín Curiel-Regueros
- Faculty of Sport Sciences, Universidad Europea de Madrid, Villaviciosa de Odón, 28670 Madrid, Spain; (V.J.C.-S.); (A.M.-R.); (A.C.-R.)
| | - Alejandro Rubio-Zarapuz
- Faculty of Sport Sciences, Universidad Europea de Madrid, Villaviciosa de Odón, 28670 Madrid, Spain; (V.J.C.-S.); (A.M.-R.); (A.C.-R.)
| | | |
Collapse
|
7
|
Fatouros P, Tsirmpas C, Andrikopoulos D, Kaplow S, Kontoangelos K, Papageorgiou C. Randomized controlled study of a digital data driven intervention for depressive and generalized anxiety symptoms. NPJ Digit Med 2025; 8:113. [PMID: 39972054 PMCID: PMC11840063 DOI: 10.1038/s41746-025-01511-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2024] [Accepted: 02/12/2025] [Indexed: 02/21/2025] Open
Abstract
As mental health disorders like Major Depressive Disorder and Generalized Anxiety Disorder rise globally, effective, scalable, and personalized treatments are urgently needed. This 16-week prospective, decentralized, randomized, waitlist-controlled study investigated the effectiveness of a digital data-driven therapeutic integrating wearable sensor data with a mobile app to deliver personalized CBT-based interventions for individuals with depressive and generalized anxiety symptoms. 200 adults were randomized to intervention or control groups, with 164 completing the study. The intervention group demonstrated significant reductions in depressive (mean change = -5.61, CI = -7.14, -4.08) and anxiety symptoms (mean change = -5.21, CI = -6.66, -3.76), compared to the control group, with medium-to-large effect sizes (r = 0.64 and r = 0.62, P < 0.001). Notably, these improvements were also observed in participants with clinically significant depression and anxiety, further reinforcing the potential of digital therapeutics in targeting more severe cases. These findings, combined with high engagement levels, suggest that data-driven digital health interventions could complement traditional treatments, though further research is needed to assess their long-term impact.
Collapse
Affiliation(s)
| | | | | | | | - Konstantinos Kontoangelos
- First Department of Psychiatry, Aiginition Hospital Medical School National and Kapodistrian University of Athens, Athens, Greece
- Neurosciences and Precision Medicine Research Institute "Costas Stefanis", University Mental Health, Athens, Greece
| | - Charalabos Papageorgiou
- Neurosciences and Precision Medicine Research Institute "Costas Stefanis", University Mental Health, Athens, Greece
| |
Collapse
|
8
|
Fernandes S, Ramos A, Vega-Barbas M, García-Vázquez C, Seoane F, Pau I. Smart Textile Technology for the Monitoring of Mental Health. SENSORS (BASEL, SWITZERLAND) 2025; 25:1148. [PMID: 40006377 PMCID: PMC11859436 DOI: 10.3390/s25041148] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/11/2025] [Revised: 02/05/2025] [Accepted: 02/12/2025] [Indexed: 02/27/2025]
Abstract
In recent years, smart devices have proven their effectiveness in monitoring mental health issues and have played a crucial role in providing therapy. The ability to embed sensors in fabrics opens new horizons for mental healthcare, addressing the growing demand for innovative solutions in monitoring and therapy. The objective of this review is to understand mental health, its impact on the human body, and the latest advancements in the field of smart textiles (sensors, electrodes, and smart garments) for monitoring physiological signals such as respiration rate (RR), electroencephalogram (EEG), electrodermal activity (EDA), electrocardiogram (ECG), and cortisol, all of which are associated with mental health disorders. Databases such as Web of Science (WoS) and Scopus were used to identify studies that utilized smart textiles to monitor specific physiological parameters. Research indicates that smart textiles provide promising results compared to traditional methods, offering enhanced comfort for long-term monitoring.
Collapse
Affiliation(s)
- Shonal Fernandes
- Facultad de Diseño y Tecnología, University of Design, Innovation and Technology, 28016 Madrid, Spain; (S.F.); (A.R.); (C.G.-V.)
- ETSIS de Telecomunicación, Universidad Politécnica de Madrid, Calle Nikola Tesla S/N, 28038 Madrid, Spain; (M.V.-B.); (I.P.)
| | - Alberto Ramos
- Facultad de Diseño y Tecnología, University of Design, Innovation and Technology, 28016 Madrid, Spain; (S.F.); (A.R.); (C.G.-V.)
- Textile Materials Technology, Department of Textile Technology, Faculty of Textiles, Engineering and Business Swedish School of Textiles, University of Borås, 503 32 Boras, Sweden
| | - Mario Vega-Barbas
- ETSIS de Telecomunicación, Universidad Politécnica de Madrid, Calle Nikola Tesla S/N, 28038 Madrid, Spain; (M.V.-B.); (I.P.)
| | - Carolina García-Vázquez
- Facultad de Diseño y Tecnología, University of Design, Innovation and Technology, 28016 Madrid, Spain; (S.F.); (A.R.); (C.G.-V.)
| | - Fernando Seoane
- Textile Materials Technology, Department of Textile Technology, Faculty of Textiles, Engineering and Business Swedish School of Textiles, University of Borås, 503 32 Boras, Sweden
- Institute for Clinical Science, Intervention and Technology, Karolinska Institutet, 141 83 Stockholm, Sweden
- Department of Medical Care Technology, Karolinska University Hospital, 141 57 Huddinge, Sweden
- Department of Clinical Physiology, Karolinska University Hospital, 141 57 Huddinge, Sweden
| | - Iván Pau
- ETSIS de Telecomunicación, Universidad Politécnica de Madrid, Calle Nikola Tesla S/N, 28038 Madrid, Spain; (M.V.-B.); (I.P.)
| |
Collapse
|
9
|
Um J, Park J, Lee DE, Ahn JE, Baek JH. Machine Learning Models to Identify Individuals With Imminent Suicide Risk Using a Wearable Device: A Pilot Study. Psychiatry Investig 2025; 22:156-166. [PMID: 40017279 DOI: 10.30773/pi.2024.0257] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/22/2024] [Accepted: 12/10/2024] [Indexed: 03/01/2025] Open
Abstract
OBJECTIVE We aimed to determine whether individuals at immediate risk of suicide could be identified using data from a commercially available wearable device. METHODS Thirty-nine participants experiencing acute depressive episodes and 20 age- and sex-matched healthy controls wore a commercially available wearable device (Galaxy Watch Active2) for two months. We collected data on activities, sleep, and physiological metrics like heart rate and heart rate variability using the wearable device. Participants rated their mood spontaneously twice daily on a Likert scale displayed on the device. Mood ratings by clinicians were performed at weeks 0, 2, 4, and 8. The suicide risk was assessed using the Hamilton Depression Rating Scale's suicide item score (HAMD-3). We developed two predictive models using machine learning: a single-level model that processed all data simultaneously to identify those at immediate suicide risk (HAMD-3 scores ≥1) and a multilevel model. We compared the predictions of imminent suicide risk from both models. RESULTS Both the single-step and multi-step models effectively predicted imminent suicide risk. The multi-step model outperformed the single-step model in predicting imminent suicide risk with area under the curve scores of 0.89 compared to 0.88. In the multi-step model, the HAMD total score and heart rate variability were most significant, whereas in the single-step model, the HAMD total score and diagnosis were key predictors. CONCLUSION Wearable devices are a promising tool for identifying individuals at immediate risk of suicide. Future research with more refined temporal resolution is recommended.
Collapse
Affiliation(s)
- Jumyung Um
- Industrial & Management System Engineering, Kyung Hee University, Yongin, Republic of Korea
| | - Jongsu Park
- Graduate School of AI, Kyung Hee University, Yongin, Republic of Korea
| | - Dong Eun Lee
- Department of Psychiatry, Samsung Medical Center, Sunkyunkwan University School of Medicine, Seoul, Republic of Korea
| | - Jae Eun Ahn
- Samsung Biomedical Research Institute, Seoul, Republic of Korea
| | - Ji Hyun Baek
- Department of Psychiatry, Samsung Medical Center, Sunkyunkwan University School of Medicine, Seoul, Republic of Korea
- Dauten Family Center for Bipolar Treatment Innovation, Massachusetts General Hospital, Boston, USA
| |
Collapse
|
10
|
de Vries HJ, Delahaij R, van Zwieten M, Verhoef H, Kamphuis W. The Effects of Self-Monitoring Using a Smartwatch and Smartphone App on Stress Awareness, Self-Efficacy, and Well-Being-Related Outcomes in Police Officers: Longitudinal Mixed Design Study. JMIR Mhealth Uhealth 2025; 13:e60708. [PMID: 39881435 PMCID: PMC11793834 DOI: 10.2196/60708] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2024] [Revised: 08/15/2024] [Accepted: 10/14/2024] [Indexed: 01/31/2025] Open
Abstract
Background Wearable sensor technologies, often referred to as "wearables," have seen a rapid rise in consumer interest in recent years. Initially often seen as "activity trackers," wearables have gradually expanded to also estimate sleep, stress, and physiological recovery. In occupational settings, there is a growing interest in applying this technology to promote health and well-being, especially in professions with highly demanding working conditions such as first responders. However, it is not clear to what extent self-monitoring with wearables can positively influence stress- and well-being-related outcomes in real-life conditions and how wearable-based interventions should be designed for high-risk professionals. Objective The aim of this study was to investigate (1) whether offering a 5-week wearable-based intervention improves stress- and well-being-related outcomes in police officers and (2) whether extending a basic "off-the-shelf" wearable-based intervention with ecological momentary assessment (EMA) questionnaires, weekly personalized feedback reports, and peer support groups improves its effectiveness. Methods A total of 95 police officers from 5 offices participated in the study. The data of 79 participants were included for analysis. During the first 5 weeks, participants used no self-monitoring technology (control period). During the following 5 weeks (intervention period), 41 participants used a Garmin Forerunner 255 smartwatch with a custom-built app (comparable to that of the consumer-available wearable), whereas the other 38 participants used the same system, but complemented by daily EMA questionnaires, weekly personalized feedback reports, and access to peer support groups. At baseline (T0) and after the control (T1) and intervention (T2) periods, questionnaires were administered to measure 15 outcomes relating to stress awareness, stress management self-efficacy, and outcomes related to stress and general well-being. Linear mixed models that accounted for repeated measures within subjects, the control and intervention periods, and between-group differences were used to address both research questions. Results The results of the first analysis showed that the intervention had a small (absolute Hedges g=0.25-0.46) but consistent effect on 8 of 15 of the stress- and well-being-related outcomes in comparison to the control group. The second analysis provided mixed results; the extended intervention was more effective than the basic intervention at improving recovery after work but less effective at improving self-efficacy in behavior change and sleep issues, and similarly effective in the remaining 12 outcomes. Conclusions Offering a 5-week wearable-based intervention to police officers can positively contribute to optimizing their stress-related, self-efficacy, and well-being-related outcomes. Complementing the basic "off-the-shelf" wearable-based intervention with additional EMA questionnaires, weekly personalized feedback reports, and peer support groups did not appear to improve the effectiveness of the intervention. Future work is needed to investigate how different aspects of these interventions can be tailored to specific characteristics and needs of employees to optimize these effects.
Collapse
Affiliation(s)
- Herman Jaap de Vries
- Department of Learning and Workforce Development, The Netherlands Organisation for Applied Scientific Research, Soesterberg, Netherlands
| | - Roos Delahaij
- Department of Learning and Workforce Development, The Netherlands Organisation for Applied Scientific Research, Soesterberg, Netherlands
| | - Marianne van Zwieten
- Department of Work Health Technology, The Netherlands Organisation for Applied Scientific Research, Leiden, Netherlands
| | - Helen Verhoef
- Department of Sustainable Productivity and Employability, The Netherlands Organisation for Applied Scientific Research, Leiden, Netherlands
| | - Wim Kamphuis
- Department of Learning and Workforce Development, The Netherlands Organisation for Applied Scientific Research, Soesterberg, Netherlands
| |
Collapse
|
11
|
Arnold VX, Young SD. The Potential of Wearable Sensors for Detecting Cognitive Rumination: A Scoping Review. SENSORS (BASEL, SWITZERLAND) 2025; 25:654. [PMID: 39943293 PMCID: PMC11820721 DOI: 10.3390/s25030654] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/07/2024] [Revised: 01/14/2025] [Accepted: 01/17/2025] [Indexed: 02/16/2025]
Abstract
Cognitive rumination, a transdiagnostic symptom across mental health disorders, has traditionally been assessed through self-report measures. However, these measures are limited by their temporal nature and subjective bias. The rise in wearable technologies offers the potential for continuous, real-time monitoring of physiological indicators associated with rumination. This scoping review investigates the current state of research on using wearable technology to detect cognitive rumination. Specifically, we examine the sensors and wearable devices used, physiological biomarkers measured, standard measures of rumination used, and the comparative validity of specific biomarkers in identifying cognitive rumination. The review was performed according to the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines on IEEE, Scopus, PubMed, and PsycInfo databases. Studies that used wearable devices to measure rumination-related physiological responses and biomarkers were included (n = 9); seven studies assessed one biomarker, and two studies assessed two biomarkers. Electrodermal Activity (EDA) sensors capturing skin conductance activity emerged as both the most prevalent sensor (n = 5) and the most comparatively valid biomarker for detecting cognitive rumination via wearable devices. Other commonly investigated biomarkers included electrical brain activity measured through Electroencephalogram (EEG) sensors (n = 2), Heart Rate Variability (HRV) measured using Electrocardiogram (ECG) sensors and heart rate fitness monitors (n = 2), muscle response measured through Electromyography (EMG) sensors (n = 1) and movement measured through an accelerometer (n = 1). The Empatica E4 and Empatica Embrace 2 wrist-worn devices were the most frequently used wearable (n = 3). The Rumination Response Scale (RRS), was the most widely used standard scale for assessing rumination. Experimental induction protocols, often adapted from Nolen-Hoeksema and Morrow's 1993 rumination induction paradigm, were also widely used. In conclusion, the findings suggest that wearable technology offers promise in capturing real-time physiological responses associated with rumination. However, the field is still developing, and further research is needed to validate these findings and explore the impact of individual traits and contextual factors on the accuracy of rumination detection.
Collapse
Affiliation(s)
- Vitica X. Arnold
- Department of Informatics, University of California, Irvine, CA 92697, USA;
| | - Sean D. Young
- Department of Informatics, University of California, Irvine, CA 92697, USA;
- Department of Emergency Medicine, University of California, Irvine, CA 92697, USA
| |
Collapse
|
12
|
Ahn JY, Lee DK, Kim MG, Kim WJ, Park SH. Temperature-Responsive Hybrid Composite with Zero Temperature Coefficient of Resistance for Wearable Thermotherapy Pads. MICROMACHINES 2025; 16:108. [PMID: 39858763 PMCID: PMC11767656 DOI: 10.3390/mi16010108] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/16/2024] [Revised: 01/13/2025] [Accepted: 01/17/2025] [Indexed: 01/27/2025]
Abstract
Carbon-based polymer composites are widely used in wearable devices due to their exceptional electrical conductivity and flexibility. However, their temperature-dependent resistance variations pose significant challenges to device safety and performance. A negative temperature coefficient (NTC) can lead to overcurrent risks, while a positive temperature coefficient (PTC) compromises accuracy. In this study, we present a novel hybrid composite combining carbon nanotubes (CNTs) with NTC properties and carbon black (CB) with PTC properties to achieve a near-zero temperature coefficient of resistance (TCR) at an optimal ratio. This innovation enhances the safety and reliability of carbon-based polymer composites for wearable heating applications. Furthermore, a thermochromic pigment layer is integrated into the hybrid composite, enabling visual temperature indication across three distinct zones. This bilayer structure not only addresses the TCR challenge but also provides real-time, user-friendly temperature monitoring. The resulting composite demonstrates consistent performance and high precision under diverse heating conditions, making it ideal for wearable thermotherapy pads. This study highlights a significant advancement in developing multifunctional, temperature-responsive materials, offering a promising solution for safer and more controllable wearable devices.
Collapse
Affiliation(s)
| | | | | | | | - Sung-Hoon Park
- Department of Mechanical Engineering, Soongsil University, 369 Sangdo-ro, Dongjak-Gu, Seoul 06978, Republic of Korea; (J.-Y.A.); (D.-K.L.); (M.-G.K.); (W.-J.K.)
| |
Collapse
|
13
|
Sarac E. Relationship between the use of smart medical services and mental health status. World J Psychiatry 2025; 15:101246. [PMID: 39831010 PMCID: PMC11684223 DOI: 10.5498/wjp.v15.i1.101246] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/08/2024] [Revised: 11/12/2024] [Accepted: 11/21/2024] [Indexed: 12/18/2024] Open
Abstract
In this editorial, I comment on the article by Zhang et al. To emphasize the importance of the topic, I discuss the relationship between the use of smart medical devices and mental health. Smart medical services have the potential to positively influence mental health by providing monitoring, insights, and interventions. However, they also come with challenges that need to be addressed. Understanding the primary purpose for which individuals use these smart technologies is essential to tailoring them to specific mental health needs and preferences.
Collapse
Affiliation(s)
- Elif Sarac
- Ministry of National Defense, General Directorate of Management Services, Ankara 06000, Türkiye
| |
Collapse
|
14
|
Byun S, Kim AY, Shin MS, Jeon HJ, Cho CH. Automated classification of stress and relaxation responses in major depressive disorder, panic disorder, and healthy participants via heart rate variability. Front Psychiatry 2025; 15:1500310. [PMID: 39850069 PMCID: PMC11754969 DOI: 10.3389/fpsyt.2024.1500310] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/23/2024] [Accepted: 12/17/2024] [Indexed: 01/25/2025] Open
Abstract
Background Stress is a significant risk factor for psychiatric disorders such as major depressive disorder (MDD) and panic disorder (PD). This highlights the need for advanced stress-monitoring technologies to improve treatment. Stress affects the autonomic nervous system, which can be evaluated via heart rate variability (HRV). While machine learning has enabled automated stress detection via HRV in healthy individuals, its application in psychiatric patients remains underexplored. This study evaluated the feasibility of using machine-learning algorithms to detect stress automatically in MDD and PD patients, as well as healthy controls (HCs), based on HRV features. Methods The study included 147 participants (MDD: 41, PD: 47, HC: 59) who visited the laboratory up to five times over 12 weeks. HRV data were collected during stress and relaxation tasks, with 20 HRV features extracted. Random forest and multilayer perceptron classifiers were applied to distinguish between the stress and relaxation tasks. Feature importance was analyzed using SHapley Additive exPlanations, and differences in HRV between the tasks (ΔHRV) were compared across groups. The impact of personalized longitudinal scaling on classification accuracy was also assessed. Results Random forest classification accuracies were 0.67 for MDD, 0.69 for PD, and 0.73 for HCs, indicating higher accuracy in the HC group. Longitudinal scaling improved accuracies to 0.94 for MDD, 0.90 for PD, and 0.96 for HCs, suggesting its potential in monitoring patients' conditions using HRV. The HC group demonstrated greater ΔHRV fluctuation in a larger number of and more significant features than the patient groups, potentially contributing to higher accuracy. Multilayer perceptron models provided consistent results with random forest, confirming the robustness of the findings. Conclusion This study demonstrated that differentiating between stress and relaxation was more challenging in the PD and MDD groups than in the HC group, underscoring the potential of HRV metrics as stress biomarkers. Psychiatric patients exhibited altered autonomic responses, which may influence their stress reactivity. This indicates the need for a tailored approach to stress monitoring in these patient groups. Additionally, we emphasized the significance of longitudinal scaling in enhancing classification accuracy, which can be utilized to develop personalized monitoring technologies for psychiatric patients.
Collapse
Affiliation(s)
- Sangwon Byun
- Department of Electronics Engineering, Incheon National University, Incheon, Republic of Korea
| | - Ah Young Kim
- Medical Information Research Section, Electronics and Telecommunications Research Institute, Dajeon, Republic of Korea
| | - Min-Sup Shin
- Department of Psychology, Korea University, Seoul, Republic of Korea
| | - Hong Jin Jeon
- Department of Psychiatry, Depression Center, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea
- Meditrix Co., Ltd., Seoul, Republic of Korea
| | - Chul-Hyun Cho
- Department of Psychiatry, Korea University College of Medicine, Seoul, Republic of Korea
- Department of Biomedical Informatics, Korea University College of Medicine, Seoul, Republic of Korea
| |
Collapse
|
15
|
Tran TA, Eigner G, Abonyi J, Ruppert T. WEBA dataset as the Reflection of Work content effect on Workload perception in Real life Working conditions. Sci Data 2025; 12:11. [PMID: 39753583 PMCID: PMC11699040 DOI: 10.1038/s41597-024-04348-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2024] [Accepted: 12/20/2024] [Indexed: 01/06/2025] Open
Abstract
The effect of work content on workload, stress, and performance was not well addressed in the literature, due to the lack of comprehensive conceptualization, problem definition, and relevant dataset. The gap between laboratory-simulated studies and real-life working conditions delays the generalization, hindering the development of performance management and monitoring tools. Contributing to this topic, a data collection effort is organized, which considers unique work conditions and work content factors of a coffee shop, to conceptualize scenarios that better highlight their effect on human performance, thus creating the Work content Effect on BAristas (WEBA) dataset. Utilizing sensor technologies to recognize the ongoing activities, physical work activities and heart rates of five baristas in 55 shifts with different work content combinations during real-life working processes were recorded, while the integration of subjective and objective measures of workload and emotions were deployed as perceived workload indicators. Heart rate signals during normal conditions without working were measured as the baseline. This dataset is unique in its conceptualization and useful for scrutinizing more nuances of the effect of work content on performance and the well-being of employees, as well as facilitating better human factor engineering, workplace and work task design.
Collapse
Affiliation(s)
- Tuan-Anh Tran
- Department of System Engineering, University of Pannonia, H-8200, Veszprem, Hungary
- HUN-REN-PE Complex Systems Monitoring Research Group, University of Pannonia, H-8200, Veszprem, Hungary
| | - György Eigner
- John von Neumann Faculty of Informatics, Biomatics and Applied Artificial Intelligence Institution, Obuda University, H-1034, Budapest, Hungary
- University Research and Innovation Center, Physiological Controls Research Center, Obuda University, H-1034, Budapest, Hungary
| | - János Abonyi
- HUN-REN-PE Complex Systems Monitoring Research Group, University of Pannonia, H-8200, Veszprem, Hungary
- Department of Process Engineering, University of Pannonia, H-8200, Veszprem, Hungary
| | - Tamás Ruppert
- Department of System Engineering, University of Pannonia, H-8200, Veszprem, Hungary.
- HUN-REN-PE Complex Systems Monitoring Research Group, University of Pannonia, H-8200, Veszprem, Hungary.
| |
Collapse
|
16
|
Tang M, Powell J, Li X. Can Wearable Technology Help Guide Dieting Safety? RESEARCH SQUARE 2024:rs.3.rs-5619684. [PMID: 39711534 PMCID: PMC11661416 DOI: 10.21203/rs.3.rs-5619684/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/24/2024]
Abstract
Background The safety of dietary interventions is often unmonitored. Wearable technology can track elevations in resting heart rate (RHR), a marker of physiologic stress, which may provide safety information that is incremental to self-reported data. Methods A single subject was placed on an isocaloric diet for four weeks. In weeks # 1 and 4, timing of food consumption was unregulated. In week #2, food was consumed during a three-hour feeding window (one-meal-a-day, OMAD). During week #3, food was consumed at six intervals, spaced three hours apart (6-meal diet). A Fitbit Versa™ was worn continuously, and questionnaires were administered twice daily. Results Meal frequency did not affect the subject's weight. Hunger scores from morning and night were widely split on OMAD and relatively constant on the 6-meal diet. Energy, happiness, irritability, and sleep scores were more favorable on the 6-meal diet than on OMAD. RHR extracted from the wearable device was lower during the 6-meal diet than during OMAD, especially in the late afternoon, evening, and nighttime (p<0.05). Lower RHR during the 6-meal diet corresponded to more favorable questionnaire scores. Conclusions Changes in RHR patterns acquired by wearable technology are promising indicators of physiologic stress during dietary interventions. Wearable technology can provide physiologic data that are complementary to questionnaire scores or timed manual measurements.
Collapse
Affiliation(s)
| | | | - Xiao Li
- Case Western Reserve University
| |
Collapse
|
17
|
Joseph JT, Praharaj SK. Interventional Psychiatry in India: Bridging Treatment Gaps and Expanding Horizons in Mental Health. Indian J Psychol Med 2024:02537176241294146. [PMID: 39659913 PMCID: PMC11626636 DOI: 10.1177/02537176241294146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/12/2024] Open
Affiliation(s)
- Jithin Thekkelkuthiyathottil Joseph
- Clinical Research Centre for Neuromodulation in Psychiatry, Dept. of Psychiatry, Kasturba Medical College, Manipal, Manipal Academy of Higher Education, Manipal, Karnataka, India
| | - Samir Kumar Praharaj
- Clinical Research Centre for Neuromodulation in Psychiatry, Dept. of Psychiatry, Kasturba Medical College, Manipal, Manipal Academy of Higher Education, Manipal, Karnataka, India
| |
Collapse
|
18
|
Wriessnegger SC, Leitner M, Kostoglou K. The brain under pressure: Exploring neurophysiological responses to cognitive stress. Brain Cogn 2024; 182:106239. [PMID: 39556965 DOI: 10.1016/j.bandc.2024.106239] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2024] [Accepted: 11/04/2024] [Indexed: 11/20/2024]
Abstract
Stress is an increasingly dominating part of our daily lives and higher performance requirements at work or to ourselves influence the physiological reaction of our body. Elevated stress levels can be reliably identified through electroencephalogram (EEG) and heart rate (HR) measurements. In this study, we examined how an arithmetic stress-inducing task impacted EEG and HR, establishing meaningful correlations between behavioral data and physiological recordings. Thirty-one healthy participants (15 females, 16 males, aged 20 to 37) willingly participated. Under time pressure, participants completed arithmetic calculations and filled out stress questionnaires before and after the task. Linear mixed effects (LME) allowed us to generate topographical association maps showing significant relations between EEG features (delta, theta, alpha, beta, and gamma power) and factors such as task difficulty, error rate, response time, stress scores, and HR. With task difficulty, we observed left centroparietal and parieto-occipital theta power decreases, and alpha power increases. Furthermore, frontal alpha, delta and theta activity increased with error rate and relative response time, while parieto-temporo-occipital alpha power decreased. Practice effects on EEG power included increases in temporal, parietal, and parieto-occipital theta and alpha activity. HR was positively associated with frontal delta, theta and alpha power whereas frontal gamma power decreases. Significant alpha laterality scores were observed for all factors except task difficulty and relative response time, showing overall increases in left parietal regions. Significant frontal alpha asymmetries emerged with increases in error rate, sex, run number, and HR and occipital alpha asymmetries were also found with run number and HR. Additionally we explored practice effects and noted sex-related differences in EEG features, HR, and questionnaire scores. Overall, our study enhances the understanding of EEG/ECG-based mental stress detection, crucial for early interventions, personalized treatment and objective stress assessment towards the development of a neuroadaptive system.
Collapse
Affiliation(s)
- S C Wriessnegger
- Institute of Neural Engineering, Graz University of Technology, Graz, Austria; BioTechMed-Graz, Graz, Austria
| | - M Leitner
- Institute of Neural Engineering, Graz University of Technology, Graz, Austria
| | - K Kostoglou
- Institute of Neural Engineering, Graz University of Technology, Graz, Austria
| |
Collapse
|
19
|
Yammouri G, Ait Lahcen A. AI-Reinforced Wearable Sensors and Intelligent Point-of-Care Tests. J Pers Med 2024; 14:1088. [PMID: 39590580 PMCID: PMC11595538 DOI: 10.3390/jpm14111088] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2024] [Revised: 10/25/2024] [Accepted: 10/28/2024] [Indexed: 11/28/2024] Open
Abstract
Artificial intelligence (AI) techniques offer great potential to advance point-of-care testing (POCT) and wearable sensors for personalized medicine applications. This review explores the recent advances and the transformative potential of the use of AI in improving wearables and POCT. The integration of AI significantly contributes to empowering these tools and enables continuous monitoring, real-time analysis, and rapid diagnostics, thus enhancing patient outcomes and healthcare efficiency. Wearable sensors powered by AI models offer tremendous opportunities for precise and non-invasive tracking of physiological conditions that are essential for early disease detection and personalized treatments. AI-empowered POCT facilitates rapid, accurate diagnostics, making these medical testing kits accessible and available even in resource-limited settings. This review discusses the key advances in AI applications for data processing, sensor fusion, and multivariate analytics, highlighting case examples that exhibit their impact in different medical scenarios. In addition, the challenges associated with data privacy, regulatory approvals, and technology integrations into the existing healthcare system have been overviewed. The outlook emphasizes the urgent need for continued innovation in AI-driven health technologies to overcome these challenges and to fully achieve the potential of these techniques to revolutionize personalized medicine.
Collapse
Affiliation(s)
- Ghita Yammouri
- Chemical Analysis & Biosensors, Process Engineering and Environment Laboratory, Faculty of Science and Techniques, Hassan II University of Casablanca, Mohammedia 28806, Morocco;
| | | |
Collapse
|
20
|
Song M, Yang Z, Triantafyllopoulos A, Zhang Z, Nan Z, Tang M, Takeuchi H, Nakamura T, Kishi A, Ishizawa T, Yoshiuchi K, Schuller B, Yamamoto Y. Empowering Mental Health Monitoring Using a Macro-Micro Personalization Framework for Multimodal-Multitask Learning: Descriptive Study. JMIR Ment Health 2024; 11:e59512. [PMID: 39422993 PMCID: PMC11530727 DOI: 10.2196/59512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/14/2024] [Revised: 07/16/2024] [Accepted: 08/03/2024] [Indexed: 10/19/2024] Open
Abstract
BACKGROUND The field of mental health technology presently has significant gaps that need addressing, particularly in the domain of daily monitoring and personalized assessments. Current noninvasive devices such as wristbands and smartphones are capable of collecting a wide range of data, which has not yet been fully used for mental health monitoring. OBJECTIVE This study aims to introduce a novel dataset for personalized daily mental health monitoring and a new macro-micro framework. This framework is designed to use multimodal and multitask learning strategies for improved personalization and prediction of emotional states in individuals. METHODS Data were collected from 298 individuals using wristbands and smartphones, capturing physiological signals, speech data, and self-annotated emotional states. The proposed framework combines macro-level emotion transformer embeddings with micro-level personalization layers specific to each user. It also introduces a Dynamic Restrained Uncertainty Weighting method to effectively integrate various data types for a balanced representation of emotional states. Several fusion techniques, personalization strategies, and multitask learning approaches were explored. RESULTS The proposed framework was evaluated using the concordance correlation coefficient, resulting in a score of 0.503. This result demonstrates the framework's efficacy in predicting emotional states. CONCLUSIONS The study concludes that the proposed multimodal and multitask learning framework, which leverages transformer-based techniques and dynamic task weighting strategies, is superior for the personalized monitoring of mental health. The study indicates the potential of transforming daily mental health monitoring into a more personalized app, opening up new avenues for technology-based mental health interventions.
Collapse
Affiliation(s)
- Meishu Song
- Educational Physiology Laboratory, Graduate School of Education, The University of Tokyo, Tokyo, Japan
| | - Zijiang Yang
- Educational Physiology Laboratory, Graduate School of Education, The University of Tokyo, Tokyo, Japan
| | | | | | - Zhe Nan
- Google, San Carlos, CA, United States
| | - Muxuan Tang
- Educational Physiology Laboratory, Graduate School of Education, The University of Tokyo, Tokyo, Japan
| | - Hiroki Takeuchi
- Educational Physiology Laboratory, Graduate School of Education, The University of Tokyo, Tokyo, Japan
| | | | - Akifumi Kishi
- Educational Physiology Laboratory, Graduate School of Education, The University of Tokyo, Tokyo, Japan
| | - Tetsuro Ishizawa
- Educational Physiology Laboratory, Graduate School of Education, The University of Tokyo, Tokyo, Japan
| | - Kazuhiro Yoshiuchi
- Educational Physiology Laboratory, Graduate School of Education, The University of Tokyo, Tokyo, Japan
| | | | - Yoshiharu Yamamoto
- Educational Physiology Laboratory, Graduate School of Education, The University of Tokyo, Tokyo, Japan
| |
Collapse
|
21
|
Teo JT, Johnstone SJ, Thomas SJ. Brain and heart activity during interactions with pet dogs: A portable electroencephalogram and heart rate variability study. Int J Psychophysiol 2024; 204:112412. [PMID: 39111638 DOI: 10.1016/j.ijpsycho.2024.112412] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2024] [Revised: 06/11/2024] [Accepted: 08/03/2024] [Indexed: 08/19/2024]
Abstract
Dog ownership has been linked to numerous benefits to human health and wellbeing. However, due to the lack of previous research on changes to brain activity during interactions with pet dogs, the underlying psychophysiological mechanisms are still unclear. The aim of the present study was to examine changes in heart rate (HR), heart rate variability (HRV), and electroencephalogram (EEG) power during interactions between dog owners and their pet dog. Fifty healthy adult dog owners completed baseline psychological measures and pet attachment scales. Subjective units of relaxation (SUR) as well as continuous EEG, HR, and HRV via portable devices were measured during five experimental conditions (baseline resting, relaxation-induction exercise, patting a toy dog, real dog present, and patting a real dog) in participants' homes. SUR was higher in all experimental conditions than at baseline. SUR was also higher during dog interaction than when the dog was present with no interaction. However, SUR during dog interaction was not significantly different from the toy dog and relaxation induction condition. Higher delta, theta, alpha, beta power and HR were found during dog interaction than all other conditions. Higher HRV was found during dog interaction compared to baseline, patting a toy dog, and relaxation-induction exercise, but not significantly different from the real dog present only condition. Lastly, overall HR correlated with psychological measures. Overall, the results show that there are significant changes in brain and heart activity when humans interact with pet dogs, consistent with increases in relaxation and focussed attention. These findings are relevant to understanding the potential mechanisms for health benefits associated with pets.
Collapse
Affiliation(s)
- Jillian T Teo
- School of Psychology, Faculty of the Arts, Social Sciences and Humanities, University of Wollongong, Wollongong, NSW 2522, Australia.
| | - Stuart J Johnstone
- School of Psychology, Faculty of the Arts, Social Sciences and Humanities, University of Wollongong, Wollongong, NSW 2522, Australia.
| | - Susan J Thomas
- Graduate School of Medicine, Faculty of Science, Medicine and Health, University of Wollongong, Australia; Illawarra Health and Medical Research Institute, University of Wollongong, 2522, Australia.
| |
Collapse
|
22
|
Winslow B, Mills E. Future of service member monitoring: the intersection of biology, wearables and artificial intelligence. BMJ Mil Health 2024; 170:412-414. [PMID: 36702525 DOI: 10.1136/military-2022-002306] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2022] [Accepted: 01/15/2023] [Indexed: 01/28/2023]
Abstract
While substantial investment has been made in the early identification of mental and behavioural health disorders in service members, rates of depression, substance abuse and suicidality continue to climb. Objective and persistent measures are needed for early identification and treatment of these rising health issues. Considerable potential lies at the intersection of biology, wearables and artificial intelligence to provide high accuracy, objective monitoring of mental and behavioural health in training, operations and healthcare settings. While the current generation of wearable devices has predominantly targeted non-military use cases, military agencies have demonstrated successes in monitoring and diagnosis via off-label uses. Combined with context-aware and individualised algorithms, the integration of wearable data with artificial intelligence allows for a deeper understanding of individual-level and group-level mental and behavioural health at scale. Emerging digital phenotyping approaches which leverage ubiquitous sensing technology can provide monitoring at a greater scale, lower price point and lower individual burden by removing the need for additional body-worn technology. The intersection of this technology will enable individualised strategies to promote service member mental and physical health, reduce injury, and improve long-term well-being and deployability.
Collapse
Affiliation(s)
| | - E Mills
- Design Interactive Inc, Orlando, Florida, USA
| |
Collapse
|
23
|
Andrikopoulos D, Vassiliou G, Fatouros P, Tsirmpas C, Pehlivanidis A, Papageorgiou C. Machine learning-enabled detection of attention-deficit/hyperactivity disorder with multimodal physiological data: a case-control study. BMC Psychiatry 2024; 24:547. [PMID: 39103819 PMCID: PMC11302198 DOI: 10.1186/s12888-024-05987-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/09/2024] [Accepted: 07/25/2024] [Indexed: 08/07/2024] Open
Abstract
BACKGROUND Attention-Deficit/Hyperactivity Disorder (ADHD) is a multifaceted neurodevelopmental psychiatric condition that typically emerges during childhood but often persists into adulthood, significantly impacting individuals' functioning, relationships, productivity, and overall quality of life. However, the current diagnostic process exhibits limitations that can significantly affect its overall effectiveness. Notably, its face-to-face and time-consuming nature, coupled with the reliance on subjective recall of historical information and clinician subjectivity, stand out as key challenges. To address these limitations, objective measures such as neuropsychological evaluations, imaging techniques and physiological monitoring of the Autonomic Nervous System functioning, have been explored. METHODS The main aim of this study was to investigate whether physiological data (i.e., Electrodermal Activity, Heart Rate Variability, and Skin Temperature) can serve as meaningful indicators of ADHD, evaluating its utility in distinguishing adult ADHD patients. This observational, case-control study included a total of 76 adult participants (32 ADHD patients and 44 healthy controls) who underwent a series of Stroop tests, while their physiological data was passively collected using a multi-sensor wearable device. Univariate feature analysis was employed to identify the tests that triggered significant signal responses, while the Informative k-Nearest Neighbors (KNN) algorithm was used to filter out less informative data points. Finally, a machine-learning decision pipeline incorporating various classification algorithms, including Logistic Regression, KNN, Random Forests, and Support Vector Machines (SVM), was utilized for ADHD patient detection. RESULTS Results indicate that the SVM-based model yielded the optimal performance, achieving 81.6% accuracy, maintaining a balance between the experimental and control groups, with sensitivity and specificity of 81.4% and 81.9%, respectively. Additionally, integration of data from all physiological signals yielded the best results, suggesting that each modality captures unique aspects of ADHD. CONCLUSIONS This study underscores the potential of physiological signals as valuable diagnostic indicators of adult ADHD. For the first time, to the best of our knowledge, our findings demonstrate that multimodal physiological data collected via wearable devices can complement traditional diagnostic approaches. Further research is warranted to explore the clinical applications and long-term implications of utilizing physiological markers in ADHD diagnosis and management.
Collapse
Affiliation(s)
| | - Georgia Vassiliou
- First Department of Psychiatry, Eginition Hospital, Medical School National and Kapodistrian University of Athens, Athens, Greece
| | | | | | - Artemios Pehlivanidis
- First Department of Psychiatry, Eginition Hospital, Medical School National and Kapodistrian University of Athens, Athens, Greece
| | - Charalabos Papageorgiou
- First Department of Psychiatry, Eginition Hospital, Medical School National and Kapodistrian University of Athens, Athens, Greece
- Neurosciences and Precision Medicine Research Institute "Costas Stefanis", University Mental Health, Athens, Greece
| |
Collapse
|
24
|
Fan J, Mei J, Yang Y, Lu J, Wang Q, Yang X, Chen G, Wang R, Han Y, Sheng R, Wang W, Ding F. Sleep-phasic heart rate variability predicts stress severity: Building a machine learning-based stress prediction model. Stress Health 2024; 40:e3386. [PMID: 38411360 DOI: 10.1002/smi.3386] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Revised: 12/20/2023] [Accepted: 02/14/2024] [Indexed: 02/28/2024]
Abstract
We propose a novel approach for predicting stress severity by measuring sleep phasic heart rate variability (HRV) using a smart device. This device can potentially be applied for stress self-screening in large populations. Using a Holter electrocardiogram (ECG) and a Huawei smart device, we conducted 24-h dual recordings of 159 medical workers working regular shifts. Based on photoplethysmography (PPG) and accelerometer signals acquired by the Huawei smart device, we sorted episodes of cyclic alternating pattern (CAP; unstable sleep), non-cyclic alternating pattern (NCAP; stable sleep), wakefulness, and rapid eye movement (REM) sleep based on cardiopulmonary coupling (CPC) algorithms. We further calculated the HRV indices during NCAP, CAP and REM sleep episodes using both the Holter ECG and smart-device PPG signals. We later developed a machine learning model to predict stress severity based only on the smart device data obtained from the participants along with a clinical evaluation of emotion and stress conditions. Sleep phasic HRV indices predict individual stress severity with better performance in CAP or REM sleep than in NCAP. Using the smart device data only, the optimal machine learning-based stress prediction model exhibited accuracy of 80.3 %, sensitivity 87.2 %, and 63.9 % for specificity. Sleep phasic heart rate variability can be accurately evaluated using a smart device and subsequently can be used for stress predication.
Collapse
Affiliation(s)
- Jingjing Fan
- Department of Cardiology and Department of Neurology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Junhua Mei
- Department of Cardiology and Department of Neurology, The First Hospital of Wuhan City, Wuhan, China
| | - Yuan Yang
- Department of Cardiology and Department of Neurology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Jiajia Lu
- Department of Cardiology and Department of Neurology, The First Hospital of Wuhan City, Wuhan, China
| | - Quan Wang
- Department of Cardiology and Department of Neurology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xiaoyun Yang
- Department of Cardiology and Department of Neurology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Guohua Chen
- Department of Cardiology and Department of Neurology, The First Hospital of Wuhan City, Wuhan, China
| | - Runsen Wang
- Huawei Technologies Co., Ltd., Shenzhen, China
| | - Yujia Han
- Huawei Technologies Co., Ltd., Shenzhen, China
| | - Rong Sheng
- Huawei Technologies Co., Ltd., Shenzhen, China
| | - Wei Wang
- Department of Cardiology and Department of Neurology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Fengfei Ding
- Department of Pharmacology, Shanghai Medical College, Fudan University, Shanghai, China
| |
Collapse
|
25
|
Baron‐Shahaf D, Shahaf G. Markers of too little effort or too much alertness during neuropsychological assessment: Demonstration with perioperative changes. Brain Behav 2024; 14:e3649. [PMID: 39169455 PMCID: PMC11338839 DOI: 10.1002/brb3.3649] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/12/2024] [Revised: 07/21/2024] [Accepted: 07/22/2024] [Indexed: 08/23/2024] Open
Abstract
OBJECTIVE Cognitive assessment is based on performance in different tests. However, this performance might be hindered by lack of effective effort on the one hand, and by too much stress on the other hand. Despite their known impact, there are currently no effective tools for measuring cognitive effort or stress effect during cognitive assessment. We developed real-time electrophysiological markers for cognitive effort and for stress effect, which could be used during cognitive assessment. METHODS We assessed these markers during the use of the Montreal Cognitive Assessment (MoCA) before and after cardiac surgery, which is known to involve cognitive decline in up to 30%-50% of elderly patients. RESULTS The major findings of the study, for the largest group of patients, with preoperative MoCA in the intermediate range, were that the decline is significantly associated (1) with higher preoperative cognitive effort and (2) with higher postoperative stress effect during the test. CONCLUSIONS These findings, as well as preliminary additional ones, suggest a potential importance for monitoring cognitive effort and stress effect during assessment in general, and specifically during perioperative assessment. SIGNIFICANCE Easy-to-use markers could improve the efficacy of cognitive assessment and direct treatment generally, and specifically for perioperative decline.
Collapse
Affiliation(s)
| | - Goded Shahaf
- Applied Neurophysiology LaboratoryRambam Healthcare CampusHaifaIsrael
| |
Collapse
|
26
|
M VR, GNK G, D R, T VP, Rao GN. Neuro Receptor Signal Detecting and Monitoring Smart Devices for Biological Changes in Cognitive Health Conditions. Ann Neurosci 2024; 31:225-233. [PMID: 39156625 PMCID: PMC11325689 DOI: 10.1177/09727531231206888] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2023] [Accepted: 09/19/2023] [Indexed: 08/20/2024] Open
Abstract
Background Currently, wearable sensors significantly impact health care through continuous monitoring and event prediction. The types and clinical applications of wearable technology for the prevention of mental illnesses, as well as associated health authority rules, are covered in the current review. Summary The technologies behind wearable ECG monitors, biosensors, electronic skin patches, neural interfaces, retinal prosthesis, and smart contact lenses were discussed. We described how sensors will examine neuronal impulses using verified machine-learning algorithms running in real-time. These sensors will closely monitor body signals and demonstrate continuous sensing with wireless functionality. The wearable applications in the following medical fields were covered in our review: sleep, neurology, mental health, anxiety, depression, Parkinson's disease, epilepsy, seizures, and schizophrenia. These mental health conditions can cause serious issues, even death. Inflammation brought on by mental health problems can worsen hypothalamic-pituitary-adrenal axis dysfunction and interfere with certain neuroregulatory systems such as the neural peptide Y, serotonergic, and cholinergic systems. Severe depressive disorder symptoms are correlated with elevated Interleukin (IL-6) levels. On the basis of previous and present data collected utilizing a variety of sensory modalities, researchers are currently investigating ways to identify or detect the current mental state. Key message This review explores the potential of various mental health monitoring technologies. The types and clinical uses of wearable technology, such as ECG monitors, biosensors, electronic skin patches, brain interfaces, retinal prostheses, and smart contact lenses, were covered in the current review will be beneficial for patients with mental health problems like Alzheimer, epilepsy, dementia. The sensors will closely monitor bodily signals with wireless functionality while using machine learning algorithms to analyse neural impulses in real time.
Collapse
Affiliation(s)
- Vivek Reddy M
- Department of Regulatory Affairs, JSS College of Pharmacy, JSS Academy of Higher Education & Research, Ooty, Nilgiris, Tamil Nadu, India
| | - Ganesh GNK
- Department of Regulatory Affairs, JSS College of Pharmacy, JSS Academy of Higher Education & Research, Ooty, Nilgiris, Tamil Nadu, India
| | - Rudhresh D
- Department of Regulatory Affairs, JSS College of Pharmacy, JSS Academy of Higher Education & Research, Ooty, Nilgiris, Tamil Nadu, India
| | - Vaishnavi Parimala T
- Department of Regulatory Affairs, JSS College of Pharmacy, JSS Academy of Higher Education & Research, Ooty, Nilgiris, Tamil Nadu, India
| | - Gaddam Narasimha Rao
- Department of Pharmacology, JSS College of Pharmacy, JSS Academy of Higher Education & Research, Ooty, Nilgiris, Tamil Nadu, India
| |
Collapse
|
27
|
Zhang L, Nathan V, Rosa C, Kuang J, Mendes WB, Alex Gao J. Morphological Photoplethysmography Features Enhance Stress Detection in Earbud Sensors. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2024; 2024:1-5. [PMID: 40039231 DOI: 10.1109/embc53108.2024.10782695] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/06/2025]
Abstract
Stress monitoring has become a focal interest in health sensing due to the mental and physical effects of long-term stress. Recent work demonstrated the feasibility of photoplethysmography (PPG)-based heart rate variability (HRV) features from earbud sensors to detect stress. However, morphological PPG features from earbuds have not been evaluated for stress detection. We analyzed physiological data from periods of stress and non-stress for 97 subjects. We trained machine learning models on PPG morphological features and HRV features from the earbuds, as well as ECG HRV features from a reference device. The morphological features (F1 score: 0.879) outperformed PPG HRV features (F1 score: 0.773) in stress classification. The combination of PPG morphological features and HRV features (F1 score: 0.880) performed similarly to ECG HRV features (F1 score: 0.887; ∆F1% = 0.798%). The results suggest earbud PPG morphological and HRV features can detect stress with similar fidelity to ECG, despite the smaller form factor and limited sampling rate. Thus, earbud sensors may be a strong candidate for stress monitoring in physiology due to their user-friendly and comfortable nature.
Collapse
|
28
|
Zhang R, Fang R, Orooji M, Homayoun H. Introducing We-Be Band: an End-to-end Platform for Continuous Health Monitoring. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2024; 2024:1-5. [PMID: 40040220 DOI: 10.1109/embc53108.2024.10781832] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/06/2025]
Abstract
This paper introduces We-Be band, a significant leap in wearable technology for real-time physiological monitoring. The device includes Photoplethysmography (PPG) for cardiovascular health, Electrodermal Activity (EDA) for stress and emotional response, Skin Temperature for body heat regulation, and an Accelerometer (ACC) for physical activity tracking. This sensor array enables real-time, in-depth biofeedback and data collection. Additionally, the We-Be band incorporates Bluetooth Low Energy (BLE) for efficient data transmission to our mobile app, allowing users to view their health data in real-time. Its ultra-low-power design ensures a battery life of upto 14 days on typical usage, emphasizing convenience and continuous monitoring without frequent recharges. The device's ecosystem supports extensive customization and research application flexibility, thanks to its open-source API, mobile app integration, and cloud connectivity. This versatility makes the We-Be band an adaptable tool for scientific research. Crucially, our subject experiments confirm that the We-Be band delivers data quality comparable to gold standard medical grade devices in the field. This finding highlights its accuracy and suitability for research use and studies, affirming its role as a reliable and effective device for monitoring physiological parameters.
Collapse
|
29
|
He M, Cerna J, Alkurdi A, Dogan A, Zhao J, Clore JL, Sowers R, Hsiao-Wecksler ET, Hernandez ME. Physical, Social and Cognitive Stressor Identification using Electrocardiography-derived Features and Machine Learning from a Wearable Device. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2024; 2024:1-4. [PMID: 40039809 DOI: 10.1109/embc53108.2024.10782654] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/06/2025]
Abstract
Anxiety is a prevalent and detrimental mental health condition affecting young adults, particularly in college students who face a range of stressors including academic pressures, interpersonal relationships, and financial concerns. The ability to predict anxiety would help create individualized treatment. There is a need for objective and non-invasive continuous monitoring tools that allow for the prediction of anxiety. However, the generalizability of physiological changes across various stressors and participants must first be examined. The aim of this work is to examine the relationship of different stressors on heart rate variability in combination with machine learning models to assess binary and multi-class classification performance using electrocardiography derived features from a wearable device. Twenty-six college students performed a series of non-stressful and stressful conditions while wearing a Hexoskin smartshirt. The performance of binary and multi-class ML classifiers of stressor type was evaluated. Condition-wise binary classification accuracy of 76.2% and multi-class classification accuracy of 79.1% were achieved using a support vector machine (SVM) architecture. These results contribute to our understanding of individual anxiety symptom detection using ML and offer implications for applying similar monitoring tools to predict anxiety using wearable devices.
Collapse
|
30
|
Barac M, Scaletty S, Hassett LC, Stillwell A, Croarkin PE, Chauhan M, Chesak S, Bobo WV, Athreya AP, Dyrbye LN. Wearable Technologies for Detecting Burnout and Well-Being in Health Care Professionals: Scoping Review. J Med Internet Res 2024; 26:e50253. [PMID: 38916948 PMCID: PMC11234055 DOI: 10.2196/50253] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/24/2023] [Revised: 01/01/2024] [Accepted: 03/20/2024] [Indexed: 06/26/2024] Open
Abstract
BACKGROUND The occupational burnout epidemic is a growing issue, and in the United States, up to 60% of medical students, residents, physicians, and registered nurses experience symptoms. Wearable technologies may provide an opportunity to predict the onset of burnout and other forms of distress using physiological markers. OBJECTIVE This study aims to identify physiological biomarkers of burnout, and establish what gaps are currently present in the use of wearable technologies for burnout prediction among health care professionals (HCPs). METHODS A comprehensive search of several databases was performed on June 7, 2022. No date limits were set for the search. The databases were Ovid: MEDLINE(R), Embase, Healthstar, APA PsycInfo, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, Web of Science Core Collection via Clarivate Analytics, Scopus via Elsevier, EBSCOhost: Academic Search Premier, CINAHL with Full Text, and Business Source Premier. Studies observing anxiety, burnout, stress, and depression using a wearable device worn by an HCP were included, with HCP defined as medical students, residents, physicians, and nurses. Bias was assessed using the Newcastle Ottawa Quality Assessment Form for Cohort Studies. RESULTS The initial search yielded 505 papers, from which 10 (1.95%) studies were included in this review. The majority (n=9) used wrist-worn biosensors and described observational cohort studies (n=8), with a low risk of bias. While no physiological measures were reliably associated with burnout or anxiety, step count and time in bed were associated with depressive symptoms, and heart rate and heart rate variability were associated with acute stress. Studies were limited with long-term observations (eg, ≥12 months) and large sample sizes, with limited integration of wearable data with system-level information (eg, acuity) to predict burnout. Reporting standards were also insufficient, particularly in device adherence and sampling frequency used for physiological measurements. CONCLUSIONS With wearables offering promise for digital health assessments of human functioning, it is possible to see wearables as a frontier for predicting burnout. Future digital health studies exploring the utility of wearable technologies for burnout prediction should address the limitations of data standardization and strategies to improve adherence and inclusivity in study participation.
Collapse
Affiliation(s)
- Milica Barac
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN, United States
| | - Samantha Scaletty
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN, United States
| | - Leslie C Hassett
- Mayo Clinic Libraries, Mayo Clinic, Rochester, MN, United States
| | - Ashley Stillwell
- Department of Family Medicine, Mayo Clinic, Phoenix, AZ, United States
| | - Paul E Croarkin
- Department of Psychiatry and Psychology, Mayo Clinic, Rochester, MN, United States
| | - Mohit Chauhan
- Department of Psychiatry and Psychology, Mayo Clinic, Jacksonville, FL, United States
| | - Sherry Chesak
- Department of Nursing, Mayo Clinic, Rochester, MN, United States
| | - William V Bobo
- Department of Psychiatry and Psychology, Mayo Clinic, Jacksonville, FL, United States
| | - Arjun P Athreya
- Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN, United States
- Department of Psychiatry and Psychology, Mayo Clinic, Rochester, MN, United States
| | - Liselotte N Dyrbye
- Department of Medicine, University of Colorado School of Medicine, Aurora, CO, United States
| |
Collapse
|
31
|
Smokovski I, Steinle N, Behnke A, Bhaskar SMM, Grech G, Richter K, Niklewski G, Birkenbihl C, Parini P, Andrews RJ, Bauchner H, Golubnitschaja O. Digital biomarkers: 3PM approach revolutionizing chronic disease management - EPMA 2024 position. EPMA J 2024; 15:149-162. [PMID: 38841615 PMCID: PMC11147994 DOI: 10.1007/s13167-024-00364-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2024] [Accepted: 04/23/2024] [Indexed: 06/07/2024]
Abstract
Non-communicable chronic diseases (NCDs) have become a major global health concern. They constitute the leading cause of disabilities, increased morbidity, mortality, and socio-economic disasters worldwide. Medical condition-specific digital biomarker (DB) panels have emerged as valuable tools to manage NCDs. DBs refer to the measurable and quantifiable physiological, behavioral, and environmental parameters collected for an individual through innovative digital health technologies, including wearables, smart devices, and medical sensors. By leveraging digital technologies, healthcare providers can gather real-time data and insights, enabling them to deliver more proactive and tailored interventions to individuals at risk and patients diagnosed with NCDs. Continuous monitoring of relevant health parameters through wearable devices or smartphone applications allows patients and clinicians to track the progression of NCDs in real time. With the introduction of digital biomarker monitoring (DBM), a new quality of primary and secondary healthcare is being offered with promising opportunities for health risk assessment and protection against health-to-disease transitions in vulnerable sub-populations. DBM enables healthcare providers to take the most cost-effective targeted preventive measures, to detect disease developments early, and to introduce personalized interventions. Consequently, they benefit the quality of life (QoL) of affected individuals, healthcare economy, and society at large. DBM is instrumental for the paradigm shift from reactive medical services to 3PM approach promoted by the European Association for Predictive, Preventive, and Personalized Medicine (EPMA) involving 3PM experts from 55 countries worldwide. This position manuscript consolidates multi-professional expertise in the area, demonstrating clinically relevant examples and providing the roadmap for implementing 3PM concepts facilitated through DBs.
Collapse
Affiliation(s)
- Ivica Smokovski
- University Clinic of Endocrinology, Diabetes and Metabolic Disorders, Skopje, North Macedonia
- Faculty of Medical Sciences, University Goce Delcev, Stip, North Macedonia
| | - Nanette Steinle
- Veteran Affairs Capitol Health Care Network, Linthicum, MD USA
- University of Maryland School of Medicine, Baltimore, MD USA
| | - Andrew Behnke
- Endocrinology Section, Carilion Clinic, Roanoke, VA USA
- Virginia Tech Carilion School of Medicine, Roanoke, VA USA
| | - Sonu M. M. Bhaskar
- Department of Neurology, Division of Cerebrovascular Medicine and Neurology, National Cerebral and Cardiovascular Centre (NCVC), Suita, Osaka Japan
- Department of Neurology & Neurophysiology, Liverpool Hospital, Ingham Institute for Applied Medical Research and South Western Sydney Local Health District, Sydney, NSW Australia
- NSW Brain Clot Bank, Global Health Neurology Lab & NSW Health Pathology, Sydney, NSW Australia
| | - Godfrey Grech
- Department of Pathology, Faculty of Medicine & Surgery, University of Malta, Msida, Malta
| | - Kneginja Richter
- Faculty of Medical Sciences, University Goce Delcev, Stip, North Macedonia
- CuraMed Tagesklinik Nürnberg GmbH, Nuremberg, Germany
- Technische Hochschule Nürnberg GSO, Nuremberg, Germany
- University Clinic for Psychiatry and Psychotherapy, Paracelsus Medical University, Nuremberg, Germany
| | - Günter Niklewski
- University Clinic for Psychiatry and Psychotherapy, Paracelsus Medical University, Nuremberg, Germany
| | - Colin Birkenbihl
- Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston, MA USA
| | - Paolo Parini
- Cardio Metabolic Unit, Department of Medicine Huddinge, and Department of Laboratory Medicine, Karolinska Institute, and Medicine Unit of Endocrinology, Theme Inflammation and Ageing, Karolinska University Hospital, Stockholm, Sweden
| | - Russell J. Andrews
- Nanotechnology & Smart Systems Groups, NASA Ames Research Center, Aerospace Medical Association, Silicon Valley, CA USA
| | - Howard Bauchner
- Boston University Chobanian & Avedisian School of Medicine, Boston, MA USA
| | - Olga Golubnitschaja
- Predictive, Preventive and Personalized (3P) Medicine, University Hospital Bonn, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| |
Collapse
|
32
|
Kuehne C, Phillips MD, Moody S, Bryson C, Campbell IC, Conde P, Cummins N, Desrivières S, Dineley J, Dobson R, Douglas D, Folarin A, Gallop L, Hemmings A, İnce B, Mason L, Rashid Z, Bromell A, Sims C, Allen K, Bailie C, Bains P, Basher M, Battisti F, Baudinet J, Bristow K, Dawson N, Dodd L, Frater V, Freudenthal R, Gripton B, Kan C, Khor JWT, Kotze N, Laverack S, Martin L, Maxwell S, McDonald S, McKnight D, McKay R, Merrin J, Nash M, Nicholls D, Palmer S, Pearce S, Roberts C, Serpell L, Severs E, Simic M, Staton A, Westaway S, Sharpe H, Schmidt U. Characterising illness stages and recovery trajectories of eating disorders in young people via remote measurement technology (STORY): a multi-centre prospective cohort study protocol. BMC Psychiatry 2024; 24:409. [PMID: 38816707 PMCID: PMC11137943 DOI: 10.1186/s12888-024-05841-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/24/2024] [Accepted: 05/13/2024] [Indexed: 06/01/2024] Open
Abstract
BACKGROUND Eating disorders (EDs) are serious, often chronic, conditions associated with pronounced morbidity, mortality, and dysfunction increasingly affecting young people worldwide. Illness progression, stages and recovery trajectories of EDs are still poorly characterised. The STORY study dynamically and longitudinally assesses young people with different EDs (restricting; bingeing/bulimic presentations) and illness durations (earlier; later stages) compared to healthy controls. Remote measurement technology (RMT) with active and passive sensing is used to advance understanding of the heterogeneity of earlier and more progressed clinical presentations and predictors of recovery or relapse. METHODS STORY follows 720 young people aged 16-25 with EDs and 120 healthy controls for 12 months. Online self-report questionnaires regularly assess ED symptoms, psychiatric comorbidities, quality of life, and socioeconomic environment. Additional ongoing monitoring using multi-parametric RMT via smartphones and wearable smart rings ('Ōura ring') unobtrusively measures individuals' daily behaviour and physiology (e.g., Bluetooth connections, sleep, autonomic arousal). A subgroup of participants completes additional in-person cognitive and neuroimaging assessments at study-baseline and after 12 months. DISCUSSION By leveraging these large-scale longitudinal data from participants across ED diagnoses and illness durations, the STORY study seeks to elucidate potential biopsychosocial predictors of outcome, their interplay with developmental and socioemotional changes, and barriers and facilitators of recovery. STORY holds the promise of providing actionable findings that can be translated into clinical practice by informing the development of both early intervention and personalised treatment that is tailored to illness stage and individual circumstances, ultimately disrupting the long-term burden of EDs on individuals and their families.
Collapse
Affiliation(s)
- Carina Kuehne
- Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, King's College London, Psychology & Neuroscience London (IoPPN), 103 Denmark Hill, First Floor, London, SE5 8AZ, UK
| | - Matthew D Phillips
- Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, King's College London, Psychology & Neuroscience London (IoPPN), 103 Denmark Hill, First Floor, London, SE5 8AZ, UK
| | - Sarah Moody
- School of Health in Social Science, The University of Edinburgh, Edinburgh, UK
| | - Callum Bryson
- Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, King's College London, Psychology & Neuroscience London (IoPPN), 103 Denmark Hill, First Floor, London, SE5 8AZ, UK
| | - Iain C Campbell
- Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, King's College London, Psychology & Neuroscience London (IoPPN), 103 Denmark Hill, First Floor, London, SE5 8AZ, UK
| | - Pauline Conde
- Department of Biostatistics & Health Informatics, IoPPN, King's College London, London, UK
| | - Nicholas Cummins
- Department of Biostatistics & Health Informatics, IoPPN, King's College London, London, UK
| | - Sylvane Desrivières
- Social, Genetic & Developmental Psychiatry Centre, IoPPN, King's College London, London, UK
| | - Judith Dineley
- Department of Biostatistics & Health Informatics, IoPPN, King's College London, London, UK
| | - Richard Dobson
- Department of Biostatistics & Health Informatics, IoPPN, King's College London, London, UK
- NIHR Maudsley Biomedical Research Centre, London, UK
- University College London, Institute of Health Informatics, London, UK
| | - Daire Douglas
- Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, King's College London, Psychology & Neuroscience London (IoPPN), 103 Denmark Hill, First Floor, London, SE5 8AZ, UK
| | - Amos Folarin
- Department of Biostatistics & Health Informatics, IoPPN, King's College London, London, UK
- NIHR Maudsley Biomedical Research Centre, London, UK
- University College London, Institute of Health Informatics, London, UK
| | - Lucy Gallop
- Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, King's College London, Psychology & Neuroscience London (IoPPN), 103 Denmark Hill, First Floor, London, SE5 8AZ, UK
| | - Amelia Hemmings
- Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, King's College London, Psychology & Neuroscience London (IoPPN), 103 Denmark Hill, First Floor, London, SE5 8AZ, UK
| | - Başak İnce
- Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, King's College London, Psychology & Neuroscience London (IoPPN), 103 Denmark Hill, First Floor, London, SE5 8AZ, UK
| | - Luke Mason
- Department of Forensic and Neurodevelopmental Science, IoPPN, King's College London, London, UK
| | - Zulqarnain Rashid
- Department of Biostatistics & Health Informatics, IoPPN, King's College London, London, UK
| | | | | | - Karina Allen
- Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, King's College London, Psychology & Neuroscience London (IoPPN), 103 Denmark Hill, First Floor, London, SE5 8AZ, UK
- South London and Maudsley NHS Foundation Trust, London, UK
| | - Chantal Bailie
- Cornwall Partnership NHS Foundation Trus, Bodmin, Cornwall, UK
| | - Parveen Bains
- Oxford Health NHS Foundation Trust, Oxford, Oxfordshire, UK
| | - Mike Basher
- Cambridgeshire and Peterborough NHS Foundation Trust, Fulbourn, Cambridgeshire, UK
| | | | - Julian Baudinet
- Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, King's College London, Psychology & Neuroscience London (IoPPN), 103 Denmark Hill, First Floor, London, SE5 8AZ, UK
- South London and Maudsley NHS Foundation Trust, London, UK
| | - Katherine Bristow
- Cambridgeshire and Peterborough NHS Foundation Trust, Fulbourn, Cambridgeshire, UK
| | - Nicola Dawson
- Bradford District Care NHS Foundation Trust, West Yorkshire, UK
| | - Lizzie Dodd
- South West Yorkshire Partnership NHS Foundation Trust, Wakefield, UK
| | - Victoria Frater
- Cumbria Northumberland Tyne and Wear NHS Foundation Trust, Newcastle Upon Tyne, UK
| | - Robert Freudenthal
- Barnet, Enfield and Haringey Mental Health NHS Foundation Trust, London, UK
| | - Beth Gripton
- Leeds and York Partnership NHS Foundation Trust, Leeds, UK
| | - Carol Kan
- Central and North West London NHS Foundation Trust, London, UK
| | - Joel W T Khor
- South West London & St. George's Mental Health NHS Trust, St George's Eating Disorders Service, London, UK
| | - Nicus Kotze
- Dorset Healthcare University NHS Foundation Trust, Poole, Dorset, UK
| | - Stuart Laverack
- Derbyshire Healthcare NHS Foundation Trust, Derby, Derbyshire, UK
| | - Lee Martin
- Leeds and York Partnership NHS Foundation Trust, Leeds, UK
| | - Sarah Maxwell
- Norfolk and Suffolk NHS Foundation Trust, Norwich, Norfolk, UK
| | - Sarah McDonald
- Nottinghamshire Healthcare NHS Foundation Trust, Nottingham, UK
| | - Delysia McKnight
- North Staffordshire Combined Healthcare NHS Trust; Trentham, Staffordshire, UK
| | | | - Jessica Merrin
- South West Yorkshire Partnership NHS Foundation Trust, Wakefield, UK
| | - Mel Nash
- Devon Partnership NHS Foundation Trust, Exeter, Devon, UK
| | - Dasha Nicholls
- Central and North West London NHS Foundation Trust, London, UK
- Division of Psychiatry, Department of Brain Sciences, Imperial College London, London, UK
| | | | - Samantha Pearce
- Cornwall Partnership NHS Foundation Trus, Bodmin, Cornwall, UK
| | | | - Lucy Serpell
- North East London NHS Foundation Trust, London, UK
- Division of Psychology and Language Sciences, University College London, London, UK
| | | | - Mima Simic
- South London and Maudsley NHS Foundation Trust, London, UK
| | - Amelia Staton
- Nottinghamshire Healthcare NHS Foundation Trust, Nottingham, UK
| | - Sian Westaway
- Herefordshire and Worcestershire Health and Care NHS Trust, Worcester, UK
| | - Helen Sharpe
- School of Health in Social Science, The University of Edinburgh, Edinburgh, UK
| | - Ulrike Schmidt
- Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, King's College London, Psychology & Neuroscience London (IoPPN), 103 Denmark Hill, First Floor, London, SE5 8AZ, UK.
- South London and Maudsley NHS Foundation Trust, London, UK.
| |
Collapse
|
33
|
Queirolo L, Roccon A, Piovan S, Ludovichetti FS, Bacci C, Zanette G. Psychophysiological wellbeing in a class of dental students attending dental school: anxiety, burnout, post work executive performance and a 24 hours physiological investigation during a working day. Front Psychol 2024; 15:1344970. [PMID: 38845771 PMCID: PMC11154343 DOI: 10.3389/fpsyg.2024.1344970] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2023] [Accepted: 03/29/2024] [Indexed: 06/09/2024] Open
Abstract
Aim To the best of our knowledge, dental school students have never been evaluated for stress, anxiety, burnout, physiological indexes during a 24-h working day, and executive function performance post-work and post-work after returning from vacation; therefore, this research has been conducted. Methods Data were acquired at the Dental School of the University of Padua on 16 students in their 4th year, far from the exam session. While performing clinical activity on the dental chair and during a working day, electrodermal activity (EDA), heart rate variability (HRV), and heart rate (HR) were recorded. Participants' stress was measured with the Perceived Stress Scale (PSS-10 scale) and anxiety with the General Anxiety Disorder Questionnaire (GAD-7) and State-Trait Anxiety Inventory (STAI-Y-2), while burnout with the Maslach Burnout Inventory (MBI-HSS). Executive functions were evaluated using the Tower of London test (TOL-R). Results Three students (2F/1M) had a GAD-7 score ≥ 10. Five students (4F/1M) showed trait anxiety. Moderate levels of perceived stress were reported in 85% of participants. MBI-HSS showed that 7 participants scored high on emotional exhaustion and 7 on depersonalization. TOL-R performance (M = 15.85, SD = 4.01) was below the normative value p < 0.00001. A second test, after the holidays, showed normal values. EDA was higher during children's treatment (p < 0.05), ANOVA showed high HR during working time (p < 0.001), and HRV was higher in males (p < 0.001). Conclusion Based on the sample size evaluated, it is reported that being a dental student has a moderate impact on stress, anxiety, and burnout while a strong impact on executive functions buffered by rest.
Collapse
Affiliation(s)
- Luca Queirolo
- Section of Clinical Dentistry, Department of Neurosciences, University of Padua, Padua, Italy
- Department of Philosophy, Sociology, Education and Applied Psychology, University of Padua, Padua, Italy
| | - Andrea Roccon
- Section of Clinical Dentistry, Department of Neurosciences, University of Padua, Padua, Italy
| | - Silvia Piovan
- Section of Clinical Dentistry, Department of Neurosciences, University of Padua, Padua, Italy
| | | | - Christian Bacci
- Section of Clinical Dentistry, Department of Neurosciences, University of Padua, Padua, Italy
| | - Gastone Zanette
- Section of Clinical Dentistry, Department of Neurosciences, University of Padua, Padua, Italy
| |
Collapse
|
34
|
Bolpagni M, Pardini S, Dianti M, Gabrielli S. Personalized Stress Detection Using Biosignals from Wearables: A Scoping Review. SENSORS (BASEL, SWITZERLAND) 2024; 24:3221. [PMID: 38794074 PMCID: PMC11126007 DOI: 10.3390/s24103221] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/23/2024] [Revised: 05/14/2024] [Accepted: 05/16/2024] [Indexed: 05/26/2024]
Abstract
Stress is a natural yet potentially harmful aspect of human life, necessitating effective management, particularly during overwhelming experiences. This paper presents a scoping review of personalized stress detection models using wearable technology. Employing the PRISMA-ScR framework for rigorous methodological structuring, we systematically analyzed literature from key databases including Scopus, IEEE Xplore, and PubMed. Our focus was on biosignals, AI methodologies, datasets, wearable devices, and real-world implementation challenges. The review presents an overview of stress and its biological mechanisms, details the methodology for the literature search, and synthesizes the findings. It shows that biosignals, especially EDA and PPG, are frequently utilized for stress detection and demonstrate potential reliability in multimodal settings. Evidence for a trend towards deep learning models was found, although the limited comparison with traditional methods calls for further research. Concerns arise regarding the representativeness of datasets and practical challenges in deploying wearable technologies, which include issues related to data quality and privacy. Future research should aim to develop comprehensive datasets and explore AI techniques that are not only accurate but also computationally efficient and user-centric, thereby closing the gap between theoretical models and practical applications to improve the effectiveness of stress detection systems in real scenarios.
Collapse
Affiliation(s)
- Marco Bolpagni
- Human Inspired Technology Research Centre, University of Padua, 35121 Padua, Italy
- Digital Health Research, Centre for Digital Health and Wellbeing, Fondazione Bruno Kessler, 38123 Trento, Italy; (S.P.); (M.D.); (S.G.)
| | - Susanna Pardini
- Digital Health Research, Centre for Digital Health and Wellbeing, Fondazione Bruno Kessler, 38123 Trento, Italy; (S.P.); (M.D.); (S.G.)
| | - Marco Dianti
- Digital Health Research, Centre for Digital Health and Wellbeing, Fondazione Bruno Kessler, 38123 Trento, Italy; (S.P.); (M.D.); (S.G.)
| | - Silvia Gabrielli
- Digital Health Research, Centre for Digital Health and Wellbeing, Fondazione Bruno Kessler, 38123 Trento, Italy; (S.P.); (M.D.); (S.G.)
| |
Collapse
|
35
|
Latino F, Tafuri F. Wearable Sensors and the Evaluation of Physiological Performance in Elite Field Hockey Players. Sports (Basel) 2024; 12:124. [PMID: 38786993 PMCID: PMC11126008 DOI: 10.3390/sports12050124] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2024] [Revised: 04/23/2024] [Accepted: 04/26/2024] [Indexed: 05/25/2024] Open
Abstract
Sports performance tracking has gained a lot of interest and widespread use in recent years, especially in elite and sub-elite sports. This makes it possible to improve the effectiveness of training, to calibrate and balance workloads according to real energy expenditure, and to reduce the likelihood of injuries due to excessive physical stress. In this context, the aim of this review was to map the scientific literature on wearable devices used in field hockey, evaluating their characteristics and the available evidence on their validity in measuring physiological and movement parameters. A systematic investigation was carried out by employing five electronic databases and search terms that incorporated field hockey, wearables, and performance analysis. Two independent reviewers conducted assessments of the 3401 titles and abstracts for inclusion, and at the end of the screening process, 102 full texts were analyzed. Lastly, a total of 23 research articles that specifically concentrated on field hockey were incorporated. The selected papers dealt with performance monitoring (6 papers), technical analysis and strategy game (6), injury prevention (1), and physiological measurements (10). To appraise the quality of the evaluations, the Oxford quality scoring system scale was employed. The extraction of information was carried out through the utilization of the participants, intervention, comparison, and outcomes (PICOS) format. The analysis encompassed research studies that implemented wearable devices during training and competitive events. Among elite field hockey competitions, GPS units were identified as the predominant wearable, followed by heart rate monitors. The intraclass correlation coefficient (ICC) related to wearable devices showed reasonably high between-trial ICCs ranging from 0.77 to 0.99. The utilization of wearable devices in field hockey primarily centers around the measurement of player activity profiles and physiological demands. The presence of discrepancies in sampling rates and performance bands makes it arduous to draw comparisons between studies. Nevertheless, this analysis attested to the fact that wearable devices are being employed for diverse applications in the realm of field hockey.
Collapse
Affiliation(s)
- Francesca Latino
- Department of Human Science, Educational and Sport, Pegaso University, 80100 Naples, Italy
| | - Francesco Tafuri
- Heracle Lab Research in Educational Neuroscience, Niccolò Cusano University, 00100 Rome, Italy;
| |
Collapse
|
36
|
Abstract
The monitoring of vital signs in patients undergoing anesthesia began with the very first case of anesthesia and has evolved alongside the development of anesthesiology ever since. Patient monitoring started out as a manually performed, intermittent, and qualitative assessment of the patient's general well-being in the operating room. In its evolution, patient monitoring development has responded to the clinical need, for example, when critical incident studies in the 1980s found that many anesthesia adverse events could be prevented by improved monitoring, especially respiratory monitoring. It also facilitated and perhaps even enabled increasingly complex surgeries in increasingly higher-risk patients. For example, it would be very challenging to perform and provide anesthesia care during some of the very complex cardiovascular surgeries that are almost routine today without being able to simultaneously and reliably monitor multiple pressures in a variety of places in the circulatory system. Of course, anesthesia patient monitoring itself is enabled by technological developments in the world outside of the operating room. Throughout its history, anesthesia patient monitoring has taken advantage of advancements in material science (when nonthrombogenic polymers allowed the design of intravascular catheters, for example), in electronics and transducers, in computers, in displays, in information technology, and so forth. Slower product life cycles in medical devices mean that by carefully observing technologies such as consumer electronics, including user interfaces, it is possible to peek ahead and estimate with confidence the foundational technologies that will be used by patient monitors in the near future. Just as the discipline of anesthesiology has, the patient monitoring that accompanies it has come a long way from its beginnings in the mid-19th century. Extrapolating from careful observations of the prevailing trends that have shaped anesthesia patient monitoring historically, patient monitoring in the future will use noncontact technologies, will predict the trajectory of a patient's vital signs, will add regional vital signs to the current systemic ones, and will facilitate directed and supervised anesthesia care over the broader scope that anesthesia will be responsible for.
Collapse
Affiliation(s)
- Kai Kuck
- From the Departments of Anesthesiology and Biomedical Engineering, University of Utah, Salt Lake City, Utah
| | | | | |
Collapse
|
37
|
Abd-Alrazaq A, Alajlani M, Ahmad R, AlSaad R, Aziz S, Ahmed A, Alsahli M, Damseh R, Sheikh J. The Performance of Wearable AI in Detecting Stress Among Students: Systematic Review and Meta-Analysis. J Med Internet Res 2024; 26:e52622. [PMID: 38294846 PMCID: PMC10867751 DOI: 10.2196/52622] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2023] [Revised: 10/24/2023] [Accepted: 12/19/2023] [Indexed: 02/01/2024] Open
Abstract
BACKGROUND Students usually encounter stress throughout their academic path. Ongoing stressors may lead to chronic stress, adversely affecting their physical and mental well-being. Thus, early detection and monitoring of stress among students are crucial. Wearable artificial intelligence (AI) has emerged as a valuable tool for this purpose. It offers an objective, noninvasive, nonobtrusive, automated approach to continuously monitor biomarkers in real time, thereby addressing the limitations of traditional approaches such as self-reported questionnaires. OBJECTIVE This systematic review and meta-analysis aim to assess the performance of wearable AI in detecting and predicting stress among students. METHODS Search sources in this review included 7 electronic databases (MEDLINE, Embase, PsycINFO, ACM Digital Library, Scopus, IEEE Xplore, and Google Scholar). We also checked the reference lists of the included studies and checked studies that cited the included studies. The search was conducted on June 12, 2023. This review included research articles centered on the creation or application of AI algorithms for the detection or prediction of stress among students using data from wearable devices. In total, 2 independent reviewers performed study selection, data extraction, and risk-of-bias assessment. The Quality Assessment of Diagnostic Accuracy Studies-Revised tool was adapted and used to examine the risk of bias in the included studies. Evidence synthesis was conducted using narrative and statistical techniques. RESULTS This review included 5.8% (19/327) of the studies retrieved from the search sources. A meta-analysis of 37 accuracy estimates derived from 32% (6/19) of the studies revealed a pooled mean accuracy of 0.856 (95% CI 0.70-0.93). Subgroup analyses demonstrated that the accuracy of wearable AI was moderated by the number of stress classes (P=.02), type of wearable device (P=.049), location of the wearable device (P=.02), data set size (P=.009), and ground truth (P=.001). The average estimates of sensitivity, specificity, and F1-score were 0.755 (SD 0.181), 0.744 (SD 0.147), and 0.759 (SD 0.139), respectively. CONCLUSIONS Wearable AI shows promise in detecting student stress but currently has suboptimal performance. The results of the subgroup analyses should be carefully interpreted given that many of these findings may be due to other confounding factors rather than the underlying grouping characteristics. Thus, wearable AI should be used alongside other assessments (eg, clinical questionnaires) until further evidence is available. Future research should explore the ability of wearable AI to differentiate types of stress, distinguish stress from other mental health issues, predict future occurrences of stress, consider factors such as the placement of the wearable device and the methods used to assess the ground truth, and report detailed results to facilitate the conduct of meta-analyses. TRIAL REGISTRATION PROSPERO CRD42023435051; http://tinyurl.com/3fzb5rnp.
Collapse
Affiliation(s)
- Alaa Abd-Alrazaq
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Qatar Foundation, Doha, Qatar
| | - Mohannad Alajlani
- Institute of Digital Healthcare, WMG, University of Warwick, Warwick, United Kingdom
| | - Reham Ahmad
- Institute of Digital Healthcare, WMG, University of Warwick, Warwick, United Kingdom
| | - Rawan AlSaad
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Qatar Foundation, Doha, Qatar
| | - Sarah Aziz
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Qatar Foundation, Doha, Qatar
| | - Arfan Ahmed
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Qatar Foundation, Doha, Qatar
| | - Mohammed Alsahli
- Health Informatics Department, College of Health Science, Saudi Electronic University, Riyadh, Saudi Arabia
| | - Rafat Damseh
- Department of Computer Science and Software Engineering, United Arab Emirates University, Al Ain, Abu Dhabi, United Arab Emirates
| | - Javaid Sheikh
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Qatar Foundation, Doha, Qatar
| |
Collapse
|
38
|
Babu M, Lautman Z, Lin X, Sobota MHB, Snyder MP. Wearable Devices: Implications for Precision Medicine and the Future of Health Care. Annu Rev Med 2024; 75:401-415. [PMID: 37983384 DOI: 10.1146/annurev-med-052422-020437] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2023]
Abstract
Wearable devices are integrated analytical units equipped with sensitive physical, chemical, and biological sensors capable of noninvasive and continuous monitoring of vital physiological parameters. Recent advances in disciplines including electronics, computation, and material science have resulted in affordable and highly sensitive wearable devices that are routinely used for tracking and managing health and well-being. Combined with longitudinal monitoring of physiological parameters, wearables are poised to transform the early detection, diagnosis, and treatment/management of a range of clinical conditions. Smartwatches are the most commonly used wearable devices and have already demonstrated valuable biomedical potential in detecting clinical conditions such as arrhythmias, Lyme disease, inflammation, and, more recently, COVID-19 infection. Despite significant clinical promise shown in research settings, there remain major hurdles in translating the medical uses of wearables to the clinic. There is a clear need for more effective collaboration among stakeholders, including users, data scientists, clinicians, payers, and governments, to improve device security, user privacy, data standardization, regulatory approval, and clinical validity. This review examines the potential of wearables to offer affordable and reliable measures of physiological status that are on par with FDA-approved specialized medical devices. We briefly examine studies where wearables proved critical for the early detection of acute and chronic clinical conditions with a particular focus on cardiovascular disease, viral infections, and mental health. Finally, we discuss current obstacles to the clinical implementation of wearables and provide perspectives on their potential to deliver increasingly personalized proactive health care across a wide variety of conditions.
Collapse
Affiliation(s)
- Mohan Babu
- Department of Genetics, Stanford University School of Medicine, Stanford, California, USA;
| | - Ziv Lautman
- Department of Genetics, Stanford University School of Medicine, Stanford, California, USA;
- Department of Bioengineering, Stanford University School of Medicine, Stanford, California, USA
| | - Xiangping Lin
- Department of Genetics, Stanford University School of Medicine, Stanford, California, USA;
| | - Milan H B Sobota
- Department of Genetics, Stanford University School of Medicine, Stanford, California, USA;
| | - Michael P Snyder
- Department of Genetics, Stanford University School of Medicine, Stanford, California, USA;
| |
Collapse
|
39
|
Khoo LS, Lim MK, Chong CY, McNaney R. Machine Learning for Multimodal Mental Health Detection: A Systematic Review of Passive Sensing Approaches. SENSORS (BASEL, SWITZERLAND) 2024; 24:348. [PMID: 38257440 PMCID: PMC10820860 DOI: 10.3390/s24020348] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/25/2023] [Revised: 12/14/2023] [Accepted: 12/18/2023] [Indexed: 01/24/2024]
Abstract
As mental health (MH) disorders become increasingly prevalent, their multifaceted symptoms and comorbidities with other conditions introduce complexity to diagnosis, posing a risk of underdiagnosis. While machine learning (ML) has been explored to mitigate these challenges, we hypothesized that multiple data modalities support more comprehensive detection and that non-intrusive collection approaches better capture natural behaviors. To understand the current trends, we systematically reviewed 184 studies to assess feature extraction, feature fusion, and ML methodologies applied to detect MH disorders from passively sensed multimodal data, including audio and video recordings, social media, smartphones, and wearable devices. Our findings revealed varying correlations of modality-specific features in individualized contexts, potentially influenced by demographics and personalities. We also observed the growing adoption of neural network architectures for model-level fusion and as ML algorithms, which have demonstrated promising efficacy in handling high-dimensional features while modeling within and cross-modality relationships. This work provides future researchers with a clear taxonomy of methodological approaches to multimodal detection of MH disorders to inspire future methodological advancements. The comprehensive analysis also guides and supports future researchers in making informed decisions to select an optimal data source that aligns with specific use cases based on the MH disorder of interest.
Collapse
Affiliation(s)
- Lin Sze Khoo
- Department of Human-Centered Computing, Faculty of Information Technology, Monash University, Clayton, VIC 3800, Australia;
| | - Mei Kuan Lim
- School of Information Technology, Monash University Malaysia, Subang Jaya 46150, Malaysia; (M.K.L.); (C.Y.C.)
| | - Chun Yong Chong
- School of Information Technology, Monash University Malaysia, Subang Jaya 46150, Malaysia; (M.K.L.); (C.Y.C.)
| | - Roisin McNaney
- Department of Human-Centered Computing, Faculty of Information Technology, Monash University, Clayton, VIC 3800, Australia;
| |
Collapse
|
40
|
Pandya A, Lodha P, Gupta A. Technology for early detection and diagnosis of mental disorders: An evidence synthesis. DIGITAL HEALTHCARE IN ASIA AND GULF REGION FOR HEALTHY AGING AND MORE INCLUSIVE SOCIETIES 2024:37-54. [DOI: 10.1016/b978-0-443-23637-2.00019-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/10/2025]
|
41
|
Okamoto R, Terasawa E, Usui A, Matsushima M, Okayama H. The effects of online facial muscle training with resonance vocalization on mental health in postpartum women: A single-arm pilot study. WOMEN'S HEALTH (LONDON, ENGLAND) 2024; 20:17455057241286201. [PMID: 39405454 PMCID: PMC11526251 DOI: 10.1177/17455057241286201] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/06/2024] [Revised: 08/16/2024] [Accepted: 09/04/2024] [Indexed: 11/02/2024]
Abstract
BACKGROUND Mental health problems among expectant and nursing mothers also affect their infants, partners, and families. While physical activity is a potential method for preventing postpartum depression (PPD), it is difficult for postpartum women to find the time for physical exercise. A recent study reported that improving communication between expectant couples can be used as a preventive intervention for PPD, and a systematic review and meta-analysis recently reported decreased facial emotional expressivity in individuals with different non-psychotic disorders. Therefore, we focused on facial muscle training and its potential as prevention for PPD. OBJECTIVE We evaluated the effectiveness of online facial muscle training with resonance vocalization using real-time video conferencing programs on the PPD of postpartum women at 2-3 months. DESIGN We recruited 20 postpartum women and used a single-arm, prospective, pre-post design. METHODS All subjects participated in 30 min of online facial muscle training with resonance vocalization once a week for 4 weeks. The first and final sessions were performed using a real-time remote chat application, and the second and third sessions were performed on demand. Scores on the Edinburgh Postnatal Depression Scale (EPDS) as an indicator of PPD were used as the primary outcome. Secondary outcomes included the appearance ratio of a happy facial expression, analyzed using FaceReader™; mood, which was measured using a visual analog scale; and stress level, which was measured using a smartwatch. RESULTS The training had a significant effect on EPDS, appearance ratio of a happy facial expression, and mood; however, it did not affect physical stress. CONCLUSIONS In the future, intervention studies with a higher evidence level, such as a crossover randomized controlled trial, are required.
Collapse
Affiliation(s)
- Rumiko Okamoto
- Institute of Health and Sport Sciences, University of Tsukuba, Tokyo, Japan
| | - Eriko Terasawa
- Master’s and Doctoral Programs in Nursing Science, University of Tsukuba, Tsukuba, Japan
| | - Atsumi Usui
- Master’s and Doctoral Programs in Nursing Science, University of Tsukuba, Tsukuba, Japan
| | - Midori Matsushima
- Faculty of Humanities and Social Sciences, University of Tsukuba, Tsukuba, Japan
| | - Hisayo Okayama
- Master’s and Doctoral Programs in Nursing Science, University of Tsukuba, Tsukuba, Japan
- Institute of Medicine, University of Tsukuba, Tsukuba, Japan
| |
Collapse
|
42
|
Ballı M, Doğan AE, Eser HY. Improving Psychiatry Services with Artificial Intelligence: Opportunities and Challenges. TURK PSIKIYATRI DERGISI = TURKISH JOURNAL OF PSYCHIATRY 2024; 35:317-328. [PMID: 39783807 PMCID: PMC11681275 DOI: 10.5080/u27604] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/07/2024] [Accepted: 11/27/2024] [Indexed: 01/12/2025]
Abstract
Mental disorders are a critical global public health problem due to their increasing prevalence, rising costs, and significant economic burden. Despite efforts to increase the mental health workforce in Türkiye, there is a significant shortage of psychiatrists, limiting the quality and accessibility of mental health services. This review examines the potential of artificial intelligence (AI), especially large language models, to transform psychiatric care in the world and in Türkiye. AI technologies, including machine learning and deep learning, offer innovative solutions for the diagnosis, personalization of treatment, and monitoring of mental disorders using a variety of data sources, such as speech patterns, neuroimaging, and behavioral measures. Although AI has shown promising capabilities in improving diagnostic accuracy and access to mental health services, challenges such as algorithmic biases, data privacy concerns, ethical implications, and the confabulation phenomenon of large language models prevent the full implementation of AI in practice. The review highlights the need for interdisciplinary collaboration to develop culturally and linguistically adapted AI tools, particularly in the Turkish context, and suggests strategies such as fine-tuning, retrieval-augmented generation, and reinforcement learning from human feedback to increase AI reliability. Advances suggest that AI can improve mental health care by increasing diagnostic accuracy and accessibility while preserving the essential human elements of medical care. Current limitations need to be addressed through rigorous research and ethical frameworks for effective and equitable integration of AI into mental health care. Keywords: Artificial İntelligence, Health, Large Language Model, Machine Learning, Psychiatry.
Collapse
Affiliation(s)
- Muhammed Ballı
- PhD Candidate, Koç University, Graduate School of Health Sciences, Istanbul, Turkey
| | - Aslı Ercan Doğan
- Psychiatrist, Koç University School of Medicine, Department of Psychiatry, Istanbul, Turkey
| | - Hale Yapıcı Eser
- Assoc. Prof., Koç University School of Medicine, Department of Psychiatry, Istanbul, Turkey
| |
Collapse
|
43
|
Charlton PH, Allen J, Bailón R, Baker S, Behar JA, Chen F, Clifford GD, Clifton DA, Davies HJ, Ding C, Ding X, Dunn J, Elgendi M, Ferdoushi M, Franklin D, Gil E, Hassan MF, Hernesniemi J, Hu X, Ji N, Khan Y, Kontaxis S, Korhonen I, Kyriacou PA, Laguna P, Lázaro J, Lee C, Levy J, Li Y, Liu C, Liu J, Lu L, Mandic DP, Marozas V, Mejía-Mejía E, Mukkamala R, Nitzan M, Pereira T, Poon CCY, Ramella-Roman JC, Saarinen H, Shandhi MMH, Shin H, Stansby G, Tamura T, Vehkaoja A, Wang WK, Zhang YT, Zhao N, Zheng D, Zhu T. The 2023 wearable photoplethysmography roadmap. Physiol Meas 2023; 44:111001. [PMID: 37494945 PMCID: PMC10686289 DOI: 10.1088/1361-6579/acead2] [Citation(s) in RCA: 30] [Impact Index Per Article: 15.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2022] [Revised: 04/04/2023] [Accepted: 07/26/2023] [Indexed: 07/28/2023]
Abstract
Photoplethysmography is a key sensing technology which is used in wearable devices such as smartwatches and fitness trackers. Currently, photoplethysmography sensors are used to monitor physiological parameters including heart rate and heart rhythm, and to track activities like sleep and exercise. Yet, wearable photoplethysmography has potential to provide much more information on health and wellbeing, which could inform clinical decision making. This Roadmap outlines directions for research and development to realise the full potential of wearable photoplethysmography. Experts discuss key topics within the areas of sensor design, signal processing, clinical applications, and research directions. Their perspectives provide valuable guidance to researchers developing wearable photoplethysmography technology.
Collapse
Affiliation(s)
- Peter H Charlton
- Department of Public Health and Primary Care, University of Cambridge, Cambridge, CB1 8RN, United Kingdom
- Research Centre for Biomedical Engineering, City, University of London, London, EC1V 0HB, United Kingdom
| | - John Allen
- Research Centre for Intelligent Healthcare, Coventry University, Coventry, CV1 5RW, United Kingdom
- Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, NE2 4HH, United Kingdom
| | - Raquel Bailón
- Biomedical Signal Interpretation and Computational Simulation (BSICoS) Group, Aragon Institute of Engineering Research (I3A), IIS Aragon, University of Zaragoza, E-50018 Zaragoza, Spain
- CIBER-BBN, Instituto de Salud Carlos III, C/Monforte de Lemos 3-5, E-28029 Madrid, Spain
| | - Stephanie Baker
- College of Science and Engineering, James Cook University, Cairns, 4878 Queensland, Australia
| | - Joachim A Behar
- Faculty of Biomedical Engineering, Technion Israel Institute of Technology, Haifa, 3200003, Israel
| | - Fei Chen
- Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, 518055 Guandong, People’s Republic of China
| | - Gari D Clifford
- Department of Biomedical Informatics, Emory University, Atlanta, GA 30322, United States of America
- Coulter Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA 30332, United States of America
| | - David A Clifton
- Department of Engineering Science, University of Oxford, Oxford, OX3 7DQ, United Kingdom
| | - Harry J Davies
- Department of Electrical and Electronic Engineering, Imperial College London, London, SW7 2AZ, United Kingdom
| | - Cheng Ding
- Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA 30332, United States of America
- Department of Biomedical Engineering, Emory University, Atlanta, GA 30322, United States of America
| | - Xiaorong Ding
- School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, 611731, People’s Republic of China
| | - Jessilyn Dunn
- Department of Biomedical Engineering, Duke University, Durham, NC 27708-0187, United States of America
- Department of Biostatistics & Bioinformatics, Duke University, Durham, NC 27708-0187, United States of America
- Duke Clinical Research Institute, Durham, NC 27705-3976, United States of America
| | - Mohamed Elgendi
- Biomedical and Mobile Health Technology Laboratory, Department of Health Sciences and Technology, ETH Zurich, Zurich, 8008, Switzerland
| | - Munia Ferdoushi
- Department of Electrical and Computer Engineering, University of Southern California, 90089, Los Angeles, California, United States of America
- The Institute for Technology and Medical Systems (ITEMS), Keck School of Medicine, University of Southern California, Los Angeles, CA 90033, United States of America
| | - Daniel Franklin
- Institute of Biomedical Engineering, Translational Biology & Engineering Program, Ted Rogers Centre for Heart Research, University of Toronto, Toronto, M5G 1M1, Canada
| | - Eduardo Gil
- Biomedical Signal Interpretation and Computational Simulation (BSICoS) Group, Aragon Institute of Engineering Research (I3A), IIS Aragon, University of Zaragoza, E-50018 Zaragoza, Spain
- CIBER-BBN, Instituto de Salud Carlos III, C/Monforte de Lemos 3-5, E-28029 Madrid, Spain
| | - Md Farhad Hassan
- Department of Electrical and Computer Engineering, University of Southern California, 90089, Los Angeles, California, United States of America
- The Institute for Technology and Medical Systems (ITEMS), Keck School of Medicine, University of Southern California, Los Angeles, CA 90033, United States of America
| | - Jussi Hernesniemi
- Finnish Cardiovascular Research Center Tampere, Faculty of Medicine and Health Technology, Tampere University, Tampere, 33720, Finland
- Tampere Heart Hospital, Wellbeing Services County of Pirkanmaa, Tampere, 33520, Finland
| | - Xiao Hu
- Nell Hodgson Woodruff School of Nursing, Emory University, Atlanta, 30322, Georgia, United States of America
- Department of Biomedical Informatics, School of Medicine, Emory University, Atlanta, 30322, Georgia, United States of America
- Department of Computer Sciences, College of Arts and Sciences, Emory University, Atlanta, GA 30322, United States of America
| | - Nan Ji
- Hong Kong Center for Cerebrocardiovascular Health Engineering (COCHE), Hong Kong Science and Technology Park, Hong Kong, 999077, People’s Republic of China
| | - Yasser Khan
- Department of Electrical and Computer Engineering, University of Southern California, 90089, Los Angeles, California, United States of America
- The Institute for Technology and Medical Systems (ITEMS), Keck School of Medicine, University of Southern California, Los Angeles, CA 90033, United States of America
| | - Spyridon Kontaxis
- Biomedical Signal Interpretation and Computational Simulation (BSICoS) Group, Aragon Institute of Engineering Research (I3A), IIS Aragon, University of Zaragoza, E-50018 Zaragoza, Spain
- CIBER-BBN, Instituto de Salud Carlos III, C/Monforte de Lemos 3-5, E-28029 Madrid, Spain
| | - Ilkka Korhonen
- Finnish Cardiovascular Research Center Tampere, Faculty of Medicine and Health Technology, Tampere University, Tampere, 33720, Finland
| | - Panicos A Kyriacou
- Research Centre for Biomedical Engineering, City, University of London, London, EC1V 0HB, United Kingdom
| | - Pablo Laguna
- Biomedical Signal Interpretation and Computational Simulation (BSICoS) Group, Aragon Institute of Engineering Research (I3A), IIS Aragon, University of Zaragoza, E-50018 Zaragoza, Spain
- CIBER-BBN, Instituto de Salud Carlos III, C/Monforte de Lemos 3-5, E-28029 Madrid, Spain
| | - Jesús Lázaro
- Biomedical Signal Interpretation and Computational Simulation (BSICoS) Group, Aragon Institute of Engineering Research (I3A), IIS Aragon, University of Zaragoza, E-50018 Zaragoza, Spain
- CIBER-BBN, Instituto de Salud Carlos III, C/Monforte de Lemos 3-5, E-28029 Madrid, Spain
| | - Chungkeun Lee
- Digital Health Devices Division, Medical Device Evaluation Department, National Institute of Food and Drug Safety Evaluation, Ministry of Food and Drug Safety, Cheongju, 28159, Republic of Korea
| | - Jeremy Levy
- Faculty of Biomedical Engineering, Technion Israel Institute of Technology, Haifa, 3200003, Israel
- Faculty of Electrical and Computer Engineering, Technion Institute of Technology, Haifa, 3200003, Israel
| | - Yumin Li
- State Key Laboratory of Bioelectronics, School of Instrument Science and Engineering, Southeast University, Nanjing 210096, People’s Republic of China
| | - Chengyu Liu
- State Key Laboratory of Bioelectronics, School of Instrument Science and Engineering, Southeast University, Nanjing 210096, People’s Republic of China
| | - Jing Liu
- Analog Devices Inc, San Jose, CA 95124, United States of America
| | - Lei Lu
- Department of Engineering Science, University of Oxford, Oxford, OX3 7DQ, United Kingdom
| | - Danilo P Mandic
- Department of Electrical and Electronic Engineering, Imperial College London, London, SW7 2AZ, United Kingdom
| | - Vaidotas Marozas
- Department of Electronics Engineering, Kaunas University of Technology, 44249 Kaunas, Lithuania
- Biomedical Engineering Institute, Kaunas University of Technology, 44249 Kaunas, Lithuania
| | - Elisa Mejía-Mejía
- Research Centre for Biomedical Engineering, City, University of London, London, EC1V 0HB, United Kingdom
| | - Ramakrishna Mukkamala
- Department of Bioengineering and Department of Anesthesiology and Perioperative Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania, United States of America
| | - Meir Nitzan
- Department of Physics/Electro-Optic Engineering, Lev Academic Center, 91160 Jerusalem, Israel
| | - Tania Pereira
- INESC TEC—Institute for Systems and Computer Engineering, Technology and Science, Porto, 4200-465, Portugal
- Faculty of Engineering, University of Porto, Porto, 4200-465, Portugal
| | | | - Jessica C Ramella-Roman
- Department of Biomedical Engineering and Herbert Wertheim College of Medicine, Florida International University, Miami, FL 33174, United States of America
| | - Harri Saarinen
- Tampere Heart Hospital, Wellbeing Services County of Pirkanmaa, Tampere, 33520, Finland
| | - Md Mobashir Hasan Shandhi
- Department of Biomedical Engineering, Duke University, Durham, NC 27708-0187, United States of America
| | - Hangsik Shin
- Department of Digital Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, 05505, Republic of Korea
| | - Gerard Stansby
- Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, NE2 4HH, United Kingdom
- Northern Vascular Centre, Freeman Hospital, Newcastle upon Tyne, NE7 7DN, United Kingdom
| | - Toshiyo Tamura
- Future Robotics Organization, Waseda University, Tokyo, 1698050, Japan
| | - Antti Vehkaoja
- Finnish Cardiovascular Research Center Tampere, Faculty of Medicine and Health Technology, Tampere University, Tampere, 33720, Finland
- PulseOn Ltd, Espoo, 02150, Finland
| | - Will Ke Wang
- Department of Biomedical Engineering, Duke University, Durham, NC 27708-0187, United States of America
| | - Yuan-Ting Zhang
- Hong Kong Center for Cerebrocardiovascular Health Engineering (COCHE), Hong Kong Science and Technology Park, Hong Kong, 999077, People’s Republic of China
- Department of Biomedical Engineering, City University of Hong Kong, Hong Kong, 999077, People’s Republic of China
| | - Ni Zhao
- Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong
| | - Dingchang Zheng
- Research Centre for Intelligent Healthcare, Coventry University, Coventry, CV1 5RW, United Kingdom
| | - Tingting Zhu
- Department of Engineering Science, University of Oxford, Oxford, OX3 7DQ, United Kingdom
| |
Collapse
|
44
|
Dobson R, Stowell M, Warren J, Tane T, Ni L, Gu Y, McCool J, Whittaker R. Use of Consumer Wearables in Health Research: Issues and Considerations. J Med Internet Res 2023; 25:e52444. [PMID: 37988147 DOI: 10.2196/52444] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/04/2023] [Revised: 10/23/2023] [Accepted: 10/26/2023] [Indexed: 11/22/2023] Open
Abstract
As wearable devices, which allow individuals to track and self-manage their health, become more ubiquitous, the opportunities are growing for researchers to use these sensors within interventions and for data collection. They offer access to data that are captured continuously, passively, and pragmatically with minimal user burden, providing huge advantages for health research. However, the growth in their use must be coupled with consideration of their potential limitations, in particular, digital inclusion, data availability, privacy, ethics of third-party involvement, data quality, and potential for adverse consequences. In this paper, we discuss these issues and strategies used to prevent or mitigate them and recommendations for researchers using wearables as part of interventions or for data collection.
Collapse
Affiliation(s)
- Rosie Dobson
- School of Population Health, University of Auckland, Auckland, New Zealand
- Institute for Innovation and Improvement, Te Whatu Ora Waitematā, Auckland, New Zealand
| | - Melanie Stowell
- School of Population Health, University of Auckland, Auckland, New Zealand
| | - Jim Warren
- School of Computer Science, University of Auckland, Auckland, New Zealand
| | - Taria Tane
- School of Population Health, University of Auckland, Auckland, New Zealand
| | - Lin Ni
- School of Population Health, University of Auckland, Auckland, New Zealand
| | - Yulong Gu
- School of Health Sciences, Stockton University, Galloway, NJ, United States
| | - Judith McCool
- School of Population Health, University of Auckland, Auckland, New Zealand
| | - Robyn Whittaker
- School of Population Health, University of Auckland, Auckland, New Zealand
- Institute for Innovation and Improvement, Te Whatu Ora Waitematā, Auckland, New Zealand
| |
Collapse
|
45
|
Alam S, Amin MR, Faghih RT. Sparse Multichannel Decomposition of Electrodermal Activity With Physiological Priors. IEEE OPEN JOURNAL OF ENGINEERING IN MEDICINE AND BIOLOGY 2023; 4:234-250. [PMID: 38196978 PMCID: PMC10776104 DOI: 10.1109/ojemb.2023.3332839] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2022] [Revised: 08/21/2023] [Accepted: 11/07/2023] [Indexed: 01/11/2024] Open
Abstract
Goal: Inferring autonomous nervous system (ANS) activity is a challenging issue and has critical applications in stress regulation. Sweat secretions caused by ANS activity influence the electrical conductance of the skin. Therefore, the variations in skin conductance (SC) measurements reflect the sudomotor nerve activity (SMNA) and can be used to infer the underlying ANS activity. These variations are strongly correlated with emotional arousal as well as thermoregulation. However, accurately recovering ANS activity and the corresponding state-space system from a single channel signal is difficult due to artifacts introduced by measurement noise. To minimize the impact of noise on inferring ANS activity, we utilize multiple channels of SC data. Methods: We model skin conductance using a second-order differential equation incorporating a time-shifted sparse impulse train input in combination with independent cubic basis spline functions. Finally, we develop a block coordinate descent method for SC signal decomposition by employing a generalized cross-validation sparse recovery approach while including physiological priors. Results: We analyze the experimental data to validate the performance of the proposed algorithm. We demonstrate its capacity to recover the ANS activations, the underlying physiological system parameters, and both tonic and phasic components. Finally, we present an overview of the algorithm's comparative performance under varying conditions and configurations to substantiate its ability to accurately model ANS activity. Our results show that our algorithm performs better in terms of multiple metrics like noise performance, AUC score, the goodness of fit of reconstructed signal, and lower missing impulses compared with the single channel decomposition approach. Conclusion: In this study, we highlight the challenges and benefits of concurrent decomposition and deconvolution of multichannel SC signals.
Collapse
Affiliation(s)
- Samiul Alam
- Department of Electrical and Computer EngineeringUniversity of HoustonHoustonTX77004USA
| | - Md. Rafiul Amin
- Department of Electrical and Computer EngineeringUniversity of HoustonHoustonTX77004USA
| | - Rose T. Faghih
- Department of Electrical and Computer EngineeringUniversity of HoustonHoustonTX77004USA
- Department of Biomedical EngineeringNew York UniversityNew YorkNY10010USA
| |
Collapse
|
46
|
Xie F, Zhou L, Hu Q, Zeng L, Wei Y, Tang X, Gao Y, Hu Y, Xu L, Chen T, Liu H, Wang J, Lu Z, Chen Y, Zhang T. Cardiovascular variations in patients with major depressive disorder versus bipolar disorder. J Affect Disord 2023; 341:219-227. [PMID: 37657620 DOI: 10.1016/j.jad.2023.08.128] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/02/2023] [Revised: 08/14/2023] [Accepted: 08/29/2023] [Indexed: 09/03/2023]
Abstract
BACKGROUND Differentiating depression in major depressive disorder and bipolar disorder is challenging in clinical practice. Therefore, reliable biomarkers are urgently needed to differentiate between these diseases. This study's main objective was to assess whether cardiac autonomic function can distinguish patients with unipolar depression (UD), bipolar depression (BD), and bipolar mania (BM). METHODS We recruited 791 patients with mood disorders, including 191 with UD, 286 with BD, and 314 with BM, who had been drug free for at least 2 weeks. Cardiovascular status was measured using heart rate variability (HRV) and pulse wave velocity (PWV) indicators via finger photoplethysmography during a 5-min rest period. RESULTS Patients with BD showed lower HRV but higher heart rates than those with UD and BM. The PWV indicators were lower in the UD group than in the bipolar disorder group. The covariates of age, sex, and body mass index affected the cardiovascular characteristics. After adjusting for covariates, the HRV and PWV variations among the three groups remained significant. Comparisons between the UD and BD groups showed that the variable with the largest effect size was the frequency-domain indices of HRV, very low and high frequency, followed by heart rate. The area under the receiver operating characteristic curve (AUC) for each cardiovascular variable ranged from 0.661 to 0.714. The High-frequency index reached the highest AUC. LIMITATIONS Cross-sectional design and the magnitude of heterogeneity across participants with mood disorders limited our findings. CONCLUSION Patients with BD, but not BM, had a greater extent of cardiac imbalance than those with UD. Thus, HRV may serve as a psychophysiological biomarker for the differential diagnosis of UD and BD.
Collapse
Affiliation(s)
- Fei Xie
- School of Public Health, Fudan University, Shanghai, China; Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine, Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention, Shanghai Key Laboratory of Psychotic Disorders, Shanghai 200030, China
| | - LinLin Zhou
- Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine, Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention, Shanghai Key Laboratory of Psychotic Disorders, Shanghai 200030, China
| | - Qiang Hu
- Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine, Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention, Shanghai Key Laboratory of Psychotic Disorders, Shanghai 200030, China; Department of Psychiatry, ZhenJiang Mental Health Center, Zhenjiang, China
| | - LingYun Zeng
- Department of Psychiatric Rehabilitation, Shenzhen Kangning Hospital, ShenZhen, China
| | - YanYan Wei
- Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine, Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention, Shanghai Key Laboratory of Psychotic Disorders, Shanghai 200030, China
| | - XiaoChen Tang
- Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine, Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention, Shanghai Key Laboratory of Psychotic Disorders, Shanghai 200030, China
| | - YuQing Gao
- Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine, Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention, Shanghai Key Laboratory of Psychotic Disorders, Shanghai 200030, China
| | - YeGang Hu
- Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine, Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention, Shanghai Key Laboratory of Psychotic Disorders, Shanghai 200030, China
| | - LiHua Xu
- Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine, Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention, Shanghai Key Laboratory of Psychotic Disorders, Shanghai 200030, China
| | - Tao Chen
- Big Data Research Lab, University of Waterloo, Ontario, Canada; Labor and Worklife Program, Harvard University, MA, United States
| | - HaiChun Liu
- Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China
| | - JiJun Wang
- Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine, Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention, Shanghai Key Laboratory of Psychotic Disorders, Shanghai 200030, China
| | - Zheng Lu
- Department of Psychiatry, Tongji Hospital, Tongji University School of Medicine, 389 Xin Cun Road, Shanghai 200065, China.
| | - YingYao Chen
- School of Public Health, Fudan University, Shanghai, China.
| | - TianHong Zhang
- Shanghai Mental Health Center, Shanghai Jiaotong University School of Medicine, Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention, Shanghai Key Laboratory of Psychotic Disorders, Shanghai 200030, China.
| |
Collapse
|
47
|
Diaz-Ramos RE, Noriega I, Trejo LA, Stroulia E, Cao B. Using Wearable Devices and Speech Data for Personalized Machine Learning in Early Detection of Mental Disorders: Protocol for a Participatory Research Study. JMIR Res Protoc 2023; 12:e48210. [PMID: 37955959 PMCID: PMC10682927 DOI: 10.2196/48210] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2023] [Revised: 09/22/2023] [Accepted: 09/25/2023] [Indexed: 11/14/2023] Open
Abstract
BACKGROUND Early identification of mental disorder symptoms is crucial for timely treatment and reduction of recurring symptoms and disabilities. A tool to help individuals recognize warning signs is important. We posit that such a tool would have to rely on longitudinal analysis of patterns and trends in the individual's daily activities and mood, which can now be captured through data from wearable activity trackers, speech recordings from mobile devices, and the individual's own description of their mental state. In this paper, we describe such a tool developed by our team to detect early signs of depression, anxiety, and stress. OBJECTIVE This study aims to examine three questions about the effectiveness of machine learning models constructed based on multimodal data from wearables, speech, and self-reports: (1) How does speech about issues of personal context differ from speech while reading a neutral text, what type of speech data are more helpful in detecting mental health indicators, and how is the quality of the machine learning models influenced by multilanguage data? (2) Does accuracy improve with longitudinal data collection and how, and what are the most important features? and (3) How do personalized machine learning models compare against population-level models? METHODS We collect longitudinal data to aid machine learning in accurately identifying patterns of mental disorder symptoms. We developed an app that collects voice, physiological, and activity data. Physiological and activity data are provided by a variety of off-the-shelf fitness trackers, that record steps, active minutes, duration of sleeping stages (rapid eye movement, deep, and light sleep), calories consumed, distance walked, heart rate, and speed. We also collect voice recordings of users reading specific texts and answering open-ended questions chosen randomly from a set of questions without repetition. Finally, the app collects users' answers to the Depression, Anxiety, and Stress Scale. The collected data from wearable devices and voice recordings will be used to train machine learning models to predict the levels of anxiety, stress, and depression in participants. RESULTS The study is ongoing, and data collection will be completed by November 2023. We expect to recruit at least 50 participants attending 2 major universities (in Canada and Mexico) fluent in English or Spanish. The study will include participants aged between 18 and 35 years, with no communication disorders, acute neurological diseases, or history of brain damage. Data collection complied with ethical and privacy requirements. CONCLUSIONS The study aims to advance personalized machine learning for mental health; generate a data set to predict Depression, Anxiety, and Stress Scale results; and deploy a framework for early detection of depression, anxiety, and stress. Our long-term goal is to develop a noninvasive and objective method for collecting mental health data and promptly detecting mental disorder symptoms. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID) DERR1-10.2196/48210.
Collapse
Affiliation(s)
- Ramon E Diaz-Ramos
- Department of Computing Science, University of Alberta, Edmonton, AB, Canada
| | - Isabella Noriega
- School of Engineering and Sciences, Tecnologico de Monterrey, Monterrey, Mexico
| | - Luis A Trejo
- School of Engineering and Sciences, Tecnologico de Monterrey, Atizapan, Mexico
| | - Eleni Stroulia
- Department of Computing Science, University of Alberta, Edmonton, AB, Canada
| | - Bo Cao
- Department of Psychiatry, University of Alberta, Edmonton, AB, Canada
| |
Collapse
|
48
|
Abd-Alrazaq A, AlSaad R, Harfouche M, Aziz S, Ahmed A, Damseh R, Sheikh J. Wearable Artificial Intelligence for Detecting Anxiety: Systematic Review and Meta-Analysis. J Med Internet Res 2023; 25:e48754. [PMID: 37938883 PMCID: PMC10666012 DOI: 10.2196/48754] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2023] [Revised: 08/29/2023] [Accepted: 09/26/2023] [Indexed: 11/10/2023] Open
Abstract
BACKGROUND Anxiety disorders rank among the most prevalent mental disorders worldwide. Anxiety symptoms are typically evaluated using self-assessment surveys or interview-based assessment methods conducted by clinicians, which can be subjective, time-consuming, and challenging to repeat. Therefore, there is an increasing demand for using technologies capable of providing objective and early detection of anxiety. Wearable artificial intelligence (AI), the combination of AI technology and wearable devices, has been widely used to detect and predict anxiety disorders automatically, objectively, and more efficiently. OBJECTIVE This systematic review and meta-analysis aims to assess the performance of wearable AI in detecting and predicting anxiety. METHODS Relevant studies were retrieved by searching 8 electronic databases and backward and forward reference list checking. In total, 2 reviewers independently carried out study selection, data extraction, and risk-of-bias assessment. The included studies were assessed for risk of bias using a modified version of the Quality Assessment of Diagnostic Accuracy Studies-Revised. Evidence was synthesized using a narrative (ie, text and tables) and statistical (ie, meta-analysis) approach as appropriate. RESULTS Of the 918 records identified, 21 (2.3%) were included in this review. A meta-analysis of results from 81% (17/21) of the studies revealed a pooled mean accuracy of 0.82 (95% CI 0.71-0.89). Meta-analyses of results from 48% (10/21) of the studies showed a pooled mean sensitivity of 0.79 (95% CI 0.57-0.91) and a pooled mean specificity of 0.92 (95% CI 0.68-0.98). Subgroup analyses demonstrated that the performance of wearable AI was not moderated by algorithms, aims of AI, wearable devices used, status of wearable devices, data types, data sources, reference standards, and validation methods. CONCLUSIONS Although wearable AI has the potential to detect anxiety, it is not yet advanced enough for clinical use. Until further evidence shows an ideal performance of wearable AI, it should be used along with other clinical assessments. Wearable device companies need to develop devices that can promptly detect anxiety and identify specific time points during the day when anxiety levels are high. Further research is needed to differentiate types of anxiety, compare the performance of different wearable devices, and investigate the impact of the combination of wearable device data and neuroimaging data on the performance of wearable AI. TRIAL REGISTRATION PROSPERO CRD42023387560; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=387560.
Collapse
Affiliation(s)
- Alaa Abd-Alrazaq
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Cornell University, Qatar Foundation - Education City, Doha, Qatar
| | - Rawan AlSaad
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Cornell University, Qatar Foundation - Education City, Doha, Qatar
| | - Manale Harfouche
- Infectious Disease Epidemiology Group, Weill Cornell Medicine-Qatar, Cornell University, Qatar Foundation - Education City, Doha, Qatar
- World Health Organization Collaborating Centre for Disease Epidemiology Analytics on HIV/AIDS, Sexually Transmitted Infections, and Viral Hepatitis, Weill Cornell Medicine-Qatar, Cornell University, Qatar Foundation - Education City, Doha, Qatar
| | - Sarah Aziz
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Cornell University, Qatar Foundation - Education City, Doha, Qatar
| | - Arfan Ahmed
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Cornell University, Qatar Foundation - Education City, Doha, Qatar
| | - Rafat Damseh
- Department of Computer Science and Software Engineering, United Arab Emirates University, Al Ain, Abu Dhabi, United Arab Emirates
| | - Javaid Sheikh
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Cornell University, Qatar Foundation - Education City, Doha, Qatar
| |
Collapse
|
49
|
Xu Y, Zhong H, Ying S, Liu W, Chen G, Luo X, Li G. Depressive Disorder Recognition Based on Frontal EEG Signals and Deep Learning. SENSORS (BASEL, SWITZERLAND) 2023; 23:8639. [PMID: 37896732 PMCID: PMC10611358 DOI: 10.3390/s23208639] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Revised: 10/10/2023] [Accepted: 10/18/2023] [Indexed: 10/29/2023]
Abstract
Depressive disorder (DD) has become one of the most common mental diseases, seriously endangering both the affected person's psychological and physical health. Nowadays, a DD diagnosis mainly relies on the experience of clinical psychiatrists and subjective scales, lacking objective, accurate, practical, and automatic diagnosis technologies. Recently, electroencephalogram (EEG) signals have been widely applied for DD diagnosis, but mainly with high-density EEG, which can severely limit the efficiency of the EEG data acquisition and reduce the practicability of diagnostic techniques. The current study attempts to achieve accurate and practical DD diagnoses based on combining frontal six-channel electroencephalogram (EEG) signals and deep learning models. To this end, 10 min clinical resting-state EEG signals were collected from 41 DD patients and 34 healthy controls (HCs). Two deep learning models, multi-resolution convolutional neural network (MRCNN) combined with long short-term memory (LSTM) (named MRCNN-LSTM) and MRCNN combined with residual squeeze and excitation (RSE) (named MRCNN-RSE), were proposed for DD recognition. The results of this study showed that the higher EEG frequency band obtained the better classification performance for DD diagnosis. The MRCNN-RSE model achieved the highest classification accuracy of 98.48 ± 0.22% with 8-30 Hz EEG signals. These findings indicated that the proposed analytical framework can provide an accurate and practical strategy for DD diagnosis, as well as essential theoretical and technical support for the treatment and efficacy evaluation of DD.
Collapse
Affiliation(s)
- Yanting Xu
- College of Engineering, Zhejiang Normal University, Jinhua 321004, China; (Y.X.); (S.Y.)
| | - Hongyang Zhong
- College of Computer Science and Technology, Zhejiang Normal University, Jinhua 321004, China; (H.Z.); (W.L.); (G.C.)
| | - Shangyan Ying
- College of Engineering, Zhejiang Normal University, Jinhua 321004, China; (Y.X.); (S.Y.)
| | - Wei Liu
- College of Computer Science and Technology, Zhejiang Normal University, Jinhua 321004, China; (H.Z.); (W.L.); (G.C.)
| | - Guibin Chen
- College of Computer Science and Technology, Zhejiang Normal University, Jinhua 321004, China; (H.Z.); (W.L.); (G.C.)
| | - Xiaodong Luo
- The Second Hospital of Jinhua, Jinhua 321016, China
| | - Gang Li
- College of Mathematical Medicine, Zhejiang Normal University, Jinhua 321004, China
| |
Collapse
|
50
|
Roos LG, Slavich GM. Wearable technologies for health research: Opportunities, limitations, and practical and conceptual considerations. Brain Behav Immun 2023; 113:444-452. [PMID: 37557962 PMCID: PMC11233111 DOI: 10.1016/j.bbi.2023.08.008] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/27/2023] [Revised: 07/31/2023] [Accepted: 08/06/2023] [Indexed: 08/11/2023] Open
Abstract
One of the most notable limitations of laboratory-based health research is its inability to continuously monitor health-relevant physiological processes as individuals go about their daily lives. As a result, we have generated large amounts of data with unknown generalizability to real-world situations and also created a schism between where data are collected (i.e., in the lab) and where we need to intervene to prevent disease (i.e., in the field). Devices using noninvasive wearable technology are changing all of this, however, with their ability to provide high-frequency assessments of peoples' ever-changing physiological states in daily life in a manner that is relatively noninvasive, affordable, and scalable. Here, we discuss critical points that every researcher should keep in mind when using these wearables in research, spanning device and metric decisions, hardware and software selection, and data quality and sampling rate issues, using research on stress and health as an example throughout. We also address usability and participant acceptability issues, and how wearable "digital biomarker" and behavioral data can be integrated to enhance basic science and intervention studies. Finally, we summarize 10 key questions that should be addressed to make every wearable study as strong as possible. Collectively, keeping these points in mind can improve our ability to study the psychobiology of human health, and to intervene, precisely where it matters most: in peoples' daily lives.
Collapse
Affiliation(s)
- Lydia G Roos
- Department of Psychiatry and Biobehavioral Sciences, University of California Los Angeles, Los Angeles, CA, USA.
| | - George M Slavich
- Department of Psychiatry and Biobehavioral Sciences, University of California Los Angeles, Los Angeles, CA, USA
| |
Collapse
|